# 由 gen_inventory.py 从 shapes_multi.yaml 迁移:保留新上游仍存在的 op_name 键 555/601,并合并上游 core_shapes.yaml 缺失键(main:+43 vllm:+3)。 # 顶层键 = FlagGems op_name 或 Benchmark 类名(上游回退链需要); # 两者都无键的算子使用其基类 DEFAULT_SHAPES。 AttentionBenchmark: shapes: - [4, 32, 1024, 64] - [4, 32, 1024, 128] - [4, 32, 2048, 128] - [4, 32, 4096, 128] - [4, 32, 8192, 128] Benchmark: shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] BlasBenchmark: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] ChunkGatedDeltaRuleBenchmark: shape_desc: B, T, Hg, H, K, V shapes: - [1, 64, 4, 8, 64, 64] - [1, 128, 4, 8, 64, 64] - [1, 256, 4, 8, 64, 64] - [1, 512, 4, 8, 64, 64] - [2, 64, 4, 8, 64, 64] - [2, 128, 4, 8, 64, 64] - [2, 256, 4, 8, 64, 64] - [2, 512, 4, 8, 64, 64] ConcatAndCacheMLABenchmark: shapes: - [16, 8, 84, 32, 4] - [32, 4, 21, 16, 16] - [64, 8, 21, 8, 4] - [512, 64, 42, 16, 8] - [1024, 64, 84, 16, 8] ConcatBenchmark: shape_desc: ((B), M, N) * 3 shapes: - [64, 64] - [256, 256] - [512, 512] - [512, 1024] - [512, 2048] Conv1DBenchmark: shape_desc: N, C, L, Co, K, stride, padding, groups shapes: - [32, 64, 256, 64, 3, 1, 1, 1] - [64, 32, 512, 32, 5, 2, 2, 1] - [16, 16, 1024, 32, 7, 1, 3, 1] - [32, 32, 4096, 64, 9, 2, 4, 2] Conv2DBenchmark: shape_desc: N, C_in, H, W, C_out, K_h, K_w, stride, padding, groups shapes: - [32, 64, 128, 128, 32, 3, 3, 1, 1, 1] - [104, 16, 32, 32, 32, 4, 4, 1, 0, 1] - [64, 32, 18, 18, 32, 5, 5, 2, 1, 1] - [64, 32, 210, 210, 64, 5, 5, 2, 1, 1] - [16, 32, 24, 24, 24, 3, 3, 1, 1, 2] Conv3DBenchmark: shape_desc: N, C_in, D, H, W, C_out, K_d, K_h, K_w, stride, padding, groups shapes: - [32, 64, 64, 64, 64, 32, 3, 3, 3, 1, 1, 1] - [32, 64, 64, 64, 64, 32, 3, 3, 3, 2, 1, 1] - [16, 32, 24, 24, 24, 24, 3, 3, 3, 1, 1, 2] - [64, 32, 18, 18, 18, 32, 5, 5, 5, 1, 2, 1] - [16, 32, 12, 12, 12, 24, 3, 3, 3, 1, 2, 1] ConvDepthwise2DBenchmark: shape_desc: N, C, H, W, K_h, K_w, stride, padding, dilation shapes: - [32, 32, 64, 64, 3, 3, 1, 1, 1] - [16, 64, 128, 128, 3, 3, 2, 1, 1] - [8, 128, 56, 56, 5, 5, 1, 2, 1] - [4, 256, 28, 28, 3, 3, 1, 1, 2] - [2, 512, 14, 14, 3, 3, 1, 1, 1] EmbeddingBenchmark: shapes: - [4, 4] - [16, 16] - [128, 128] - [256, 256] - [1024, 1024] FlashMLABenchmark: shapes: - [1024] - [2048] - [4096] - [8192] - [16384] FractionalMaxPool2dBenchmark: shape_desc: N, C, H, W shapes: - [4, 3, 224, 224] - [16, 64, 56, 56] - [32, 128, 28, 28] - [64, 256, 14, 14] - [128, 512, 7, 7] FusedRecurrentGatedDeltaRuleBenchmark: shape_desc: (T,) many lengths shapes: - [1] - [64] - [184] - [256] - [512] GenericBenchmark2DOnly: shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] GenericBenchmark4DOnly: shapes: - [64, 64, 4, 8] - [256, 256, 4, 8] - [1024, 1024, 4, 8] - [4096, 4096, 4, 8] - [1024, 65536, 4, 8] GenericBenchmarkExcluse1D: shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] GenericBenchmarkExcluse3D: shapes: - [1048576] - [1073741824] - [1024, 512] - [1024, 1024] - [4096, 4096] IndexPutAccFalseBenchmark: shapes: - - [268435456] - - [65536] - [65536] - false - - [32, 32] - - [8] - [2, 8] - [8] - false - - [1024, 1024] - - [4, 64] - [1024] - false - - [512, 512, 512] - - [2, 128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [512] - false IndexPutAccTrueBenchmark: shapes: - - [268435456] - - [65536] - [65536] - false - - [32, 32] - - [8] - [8] - [8] - false - - [1024, 1024] - - [64] - [64] - [64] - false - - [512, 512, 512] - - [128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [2, 128] - [2, 128] - [2, 128] - false IndexReduceBenchmark: shape_desc: (B), M, N shapes: - [1048576] - [1024, 1024] - [4096, 4096] - [64, 512, 512] KronBenchmark: shapes: - [16, 16] - [64, 64] - [128, 128] - [256, 256] - [4, 8, 16, 32] MoeAlignBlockSizeBenchmark: shapes: - [16, 8] - [4, 32] - [32, 16] - [8, 64] - [128, 4] MvAndOuterBenchmark: shapes: - [384, 384] - [1024, 1024] - [4096, 4096] - [8192, 8192] - [10240, 10240] NormBenchmark: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] PerTokenGroupQuantFp8Benchmark: shapes: - [7, 512, 512] - [7, 4096, 256] - [83, 512, 64] - [2048, 4096, 256] - [2048, 13824, 512] RWKVBenchmark: shapes: - [64] - [256] - [1024] - [4096] - [8192] - [16384] - [32768] RWKVSparsityBenchmark: shapes: - [1] ReshapeAndCacheBenchmark: shapes: - [21, 4, 64, 8, 512] - [42, 8, 64, 8, 1024] - [42, 8, 80, 16, 10000] - [42, 8, 120, 32, 10000] - [42, 8, 256, 8, 1024] ReshapeAndCacheFlashBenchmark: shapes: - [21, 4, 64, 8, 512] - [21, 4, 64, 8, 1024] - [21, 4, 80, 16, 10000] - [42, 8, 64, 8, 1024] - [42, 8, 80, 16, 10000] RopeBenchmark: shapes: - [128] - [192] - [256] - [384] - [512] ScaledDotProductFusedAttentionOverrideableBenchmark: shape_desc: B, H, S, D shapes: - [2, 8, 64, 64] - [4, 8, 128, 64] - [2, 8, 128, 128] - [1, 16, 256, 64] TensorRepeatBenchmark: shape_desc: (B), M, N shapes: - [64, 64] - [256, 256] - [512, 512] - [512, 1024] - [512, 2048] TensorSelectBenchmark: shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] UnaryPointwiseBenchmark: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] UnaryReductionBenchmark: shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] UpsampleBenchmark: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] abs: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] abs_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] absolute: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] acos: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] act_quant_triton: shape_desc: M, N shapes: - [1, 128] - [1, 896] - [1, 2048] - [1, 8192] - [40, 128] - [40, 896] - [40, 2048] - [40, 8192] - [164, 128] - [164, 896] - [164, 2048] - [164, 8192] - [512, 128] - [512, 896] - [512, 2048] - [512, 8192] - [3454, 128] - [3454, 896] - [3454, 2048] - [3454, 8192] - [12027, 128] - [12027, 896] - [12027, 2048] - [12027, 8192] - [38594, 128] - [38594, 896] - [38594, 2048] - [38594, 8192] add_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] add_rms_norm: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] addcdiv: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] addcdiv_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] addcmul: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] addcmul_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] addmm: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] addmm_dtype: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] addmm_dtype_out: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] addmm_out: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] addmv: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] addr: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] alias_copy: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] alias_copy_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] all: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] all_dim: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] allclose: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] amax: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] aminmax: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] angle: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] any: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] any_dim: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] any_dims: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] apply_repetition_penalties: shape_desc: M, N shapes: - [1, 1024] - [1, 4096] - [1, 8192] - [8, 4096] - [16, 4096] - [32, 1024] - [8, 8192] - [64, 32000] apply_rotary_pos_emb: shape_desc: M, N shapes: - [128] - [192] - [256] - [384] - [512] arange: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] arange_start: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] arange_start_step: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] arcsinh: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] arcsinh_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] arcsinh_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] arctanh_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] argmax: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] argmin: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] argsort: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [1024, 1] - [1024, 512] - [16, 131072] - [8, 262144] as_strided_copy: shape_desc: input shape, size, stride, storage_offset shapes: - - [64, 64] - [64, 64] - [64, 1] - 0 - - [256, 256] - [128, 128] - [1, 256] - 0 - - [1024, 1024] - [512, 512] - [1024, 1] - 0 - - [64, 128, 64] - [32, 64, 32] - [8192, 64, 2] - 0 - - [1048576] - [524288] - [2] - 0 as_strided_copy_out: shape_desc: input shape, size, stride, storage_offset shapes: - - [64, 64] - [64, 64] - [64, 1] - 0 - - [256, 256] - [128, 128] - [1, 256] - 0 - - [1024, 1024] - [512, 512] - [1024, 1] - 0 - - [64, 128, 64] - [32, 64, 32] - [8192, 64, 2] - 0 - - [1048576] - [524288] - [2] - 0 asinh: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] asinh_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] assert_async: shape_desc: M, N shapes: - [] - [1] - [1, 1] - [1, 1, 1] atan: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] atan2: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] atan2_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] atan_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] atanh: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] avg_pool2d: shape_desc: N, C, H, W shapes: - [4, 3, 224, 224] - [16, 64, 56, 56] - [32, 128, 28, 28] - [64, 256, 14, 14] - [128, 512, 7, 7] avg_pool2d_backward: shape_desc: N, C, H, W shapes: - [4, 3, 224, 224] - [16, 64, 56, 56] - [32, 128, 28, 28] - [64, 256, 14, 14] - [128, 512, 7, 7] avg_pool3d: shape_desc: N, C, D, H, W shapes: - [4, 3, 16, 56, 56] - [8, 64, 8, 28, 28] - [16, 128, 4, 14, 14] - [32, 256, 4, 7, 7] baddbmm: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] batch_norm: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] batch_norm_backward: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] bernoulli_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bincount: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bincount_weighted: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_and_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_and_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_and_scalar_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_and_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] bitwise_and_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] bitwise_left_shift: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] bitwise_not: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] bitwise_not_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] bitwise_or_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_or_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_or_scalar_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] bitwise_or_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] bitwise_or_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] bitwise_right_shift: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] bmm: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] bmm_out: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] cat_out: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 2] - [1024, 32] - [1024, 512] - [64, 64, 1] - [64, 64, 16] cauchy: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] cauchy_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] cdist_backward: shape_desc: batch, n1, dim shapes: - [2, 16, 32] - [4, 32, 64] - [8, 64, 128] ceil: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] ceil_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] ceil_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] celu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] celu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] chunk_gated_delta_rule_fwd: shape_desc: B, T, H, K, V shapes: - [2, 16384, 16, 128, 128] - [4, 2048, 16, 128, 128] - [4, 4096, 64, 128, 128] chunk_gdn2: shapes: - [2, 512, 8, 64, 64] - [4, 1024, 8, 64, 64] - [1, 2048, 8, 64, 64] - [1, 4096, 16, 64, 64] - [1, 8192, 96, 128, 128] - [2, 2048, 16, 256, 512] - [2, 16384, 16, 128, 128] - [4, 1024, 8, 256, 512] - [4, 2048, 16, 128, 128] - [4, 4096, 64, 128, 128] - [8, 1024, 8, 64, 64] - [8, 2048, 32, 256, 256] clamp: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_max: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_max_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_min: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_min_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clamp_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clip: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] clip_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] col2im: shape_desc: M, N shapes: - - 2 - 3 - [2, 2] - [4, 5] - [1, 1] - [0, 0] - [1, 1] - - 2 - 16 - [3, 3] - [16, 16] - [1, 1] - [0, 0] - [1, 1] - - 4 - 32 - [3, 3] - [32, 32] - [1, 1] - [1, 1] - [1, 1] - - 2 - 64 - [3, 3] - [64, 64] - [2, 2] - [1, 1] - [1, 1] - - 1 - 128 - [3, 3] - [128, 128] - [1, 1] - [1, 1] - [1, 1] - - 2 - 64 - [5, 5] - [64, 64] - [2, 2] - [2, 2] - [1, 1] - - 4 - 32 - [3, 3] - [128, 128] - [2, 2] - [1, 1] - [2, 2] combine_topk_swa_indices: shape_desc: M, N shapes: - - [3, 2] - [6, 4] - [4, 3] - 4 - 4 - 2 - 20 - 8 - - [128] - [512] - [256] - 32 - 128 - 4 - 42240 - 40960 - - [512, 256] - [2048, 1024] - [1024, 512] - 64 - 256 - 4 - 45056 - 40960 - - [4096] - [4096] - [4096] - 128 - 256 - 4 - 45056 - 40960 - - [1024, 1024] - [8192, 4096] - [2048, 1024] - 128 - 256 - 4 - 45056 - 40960 - - [128] - [4096] - [512] - 32 - 256 - 128 - 5632 - 1280 - - [4096] - [4096] - [4096] - 128 - 256 - 128 - 8448 - 1280 compute_global_topk_indices_and_lens: shape_desc: M, N shapes: - [5, 4, 2, 4, 64] - [128, 32, 1, 64, 64] - [512, 64, 2, 128, 64] - [4096, 128, 1, 640, 64] - [4096, 128, 4, 640, 64] - [8192, 128, 8, 1280, 64] concat_and_cache_mla: shape_desc: M, N shapes: - [16, 8, 84, 32, 4] - [32, 4, 21, 16, 16] - [64, 8, 21, 8, 4] - [512, 64, 42, 16, 8] - [1024, 64, 84, 16, 8] concatenate: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] conj_physical: shape_desc: M, N shapes: - [256] - [2048, 2048] - [128, 512, 256] - [32, 64] - [512, 1024] - [2, 3, 4] constant_pad_nd: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] contiguous: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] conv1d: shape_desc: N, C, L, Co, K, stride, padding, groups shapes: - [32, 64, 256, 64, 3, 1, 1, 1] - [64, 32, 512, 32, 5, 2, 2, 1] - [16, 16, 1024, 32, 7, 1, 3, 1] - [32, 32, 4096, 64, 9, 2, 4, 2] - [32, 64, 512, 64, 3, 1, 0, 1] - [64, 48, 1024, 128, 5, 2, 2, 1] - [16, 24, 2048, 96, 7, 1, 3, 2] - [8, 8, 8192, 16, 11, 4, 5, 1] - [4, 4, 16384, 4, 15, 2, 7, 1] - [32, 64, 512, 64, 3, 1, valid, 1] - [64, 48, 1024, 128, 5, 2, valid, 1] - [16, 24, 2048, 96, 7, 1, same, 2] - [8, 8, 8192, 16, 11, 1, same, 1] conv1d_padding: shape_desc: batch, input_c, input_l, out_c, kernel, stride, padding, groups shapes: - [32, 64, 512, 64, 3, 1, 0, 1] - [32, 64, 512, 64, 3, 1, 1, 1] - [32, 64, 512, 64, 3, 1, 2, 1] - [64, 48, 1024, 128, 5, 2, 0, 1] - [64, 48, 1024, 128, 5, 2, 2, 1] - [64, 48, 1024, 128, 5, 2, 4, 1] - [16, 24, 2048, 96, 7, 1, 0, 2] - [16, 24, 2048, 96, 7, 1, 3, 2] - [16, 24, 2048, 96, 7, 1, 6, 2] - [32, 64, 512, 64, 3, 1, valid, 1] - [64, 48, 1024, 128, 5, 2, valid, 1] - [16, 24, 2048, 96, 7, 1, same, 2] - [8, 8, 8192, 16, 11, 1, same, 1] conv2d: shape_desc: N, C_in, H, W, C_out, K_h, K_w, stride, padding, groups shapes: - [32, 64, 128, 128, 32, 3, 3, 1, 1, 1] - [104, 16, 32, 32, 32, 4, 4, 1, 0, 1] - [64, 32, 18, 18, 32, 5, 5, 2, 1, 1] - [64, 32, 210, 210, 64, 5, 5, 2, 1, 1] - [16, 32, 24, 24, 24, 3, 3, 1, 1, 2] - [32, 64, 128, 128, 32, 3, 3, 1, 2, 1] - [32, 64, 210, 210, 16, 5, 5, 2, 1, 1] - [16, 32, 12, 12, 24, 3, 3, 2, 1, 1] - [16, 32, 24, 24, 24, 3, 3, 2, 2, 2] - [16, 32, 24, 24, 24, 3, 3, 1, 2, 2] - [16, 32, 12, 12, 24, 3, 3, 2, valid, 1] - [32, 64, 128, 128, 32, 3, 3, 1, valid, 1] - [16, 32, 24, 24, 24, 3, 3, 1, same, 2] - [32, 64, 210, 210, 16, 5, 5, 1, same, 1] conv2d_padding: shape_desc: batch, input_c, input_h, input_w, out_c, kernel_h, kernel_w, stride, padding, groups shapes: - [16, 32, 12, 12, 24, 3, 3, 1, valid, 1] - [32, 64, 128, 128, 32, 3, 3, 1, valid, 1] - [32, 64, 210, 210, 16, 5, 5, 1, valid, 1] - [16, 32, 24, 24, 24, 3, 3, 1, same, 1] - [32, 64, 128, 128, 32, 3, 3, 1, same, 1] - [32, 64, 210, 210, 16, 5, 5, 1, same, 1] - [16, 32, 24, 24, 24, 3, 3, 1, same, 2] conv3d: shape_desc: N, C_in, D, H, W, C_out, K_d, K_h, K_w, stride, padding, groups shapes: - [32, 64, 64, 64, 64, 32, 3, 3, 3, 1, 1, 1] - [32, 64, 64, 64, 64, 32, 3, 3, 3, 2, 1, 1] - [16, 32, 24, 24, 24, 24, 3, 3, 3, 1, 1, 2] - [64, 32, 18, 18, 18, 32, 5, 5, 5, 1, 2, 1] - [16, 32, 12, 12, 12, 24, 3, 3, 3, 1, 2, 1] conv3d_padding: shape_desc: batch, input_c, input_d, input_h, input_w, out_c, kernel_d, kernel_h, kernel_w, stride, padding, groups shapes: - [2, 3, 9, 9, 9, 3, 3, 3, 3, 1, valid, 1] - [9, 16, 4, 4, 4, 128, 2, 2, 2, 1, valid, 4] - [32, 8, 8, 8, 8, 32, 3, 3, 3, 1, valid, 1] - [2, 3, 9, 9, 9, 3, 3, 3, 3, 1, same, 1] - [9, 16, 4, 4, 4, 128, 2, 2, 2, 1, same, 4] - [32, 8, 8, 8, 8, 32, 3, 3, 3, 1, same, 1] conv_depthwise2d: shape_desc: N, C, H, W, K_h, K_w, stride, padding, dilation shapes: - [32, 32, 64, 64, 3, 3, 1, 1, 1] - [16, 64, 128, 128, 3, 3, 2, 1, 1] - [8, 128, 56, 56, 5, 5, 1, 2, 1] - [4, 256, 28, 28, 3, 3, 1, 1, 2] - [2, 512, 14, 14, 3, 3, 1, 1, 1] - [1, 64, 224, 224, 3, 3, 1, 1, 1] - [1, 128, 112, 112, 5, 5, 2, 2, 1] conv_transpose1d: shape_desc: batch, input_c, input_l, out_c, kernel, stride, padding, groups shapes: - [32, 64, 128, 64, 3, 1, 0, 1] - [64, 48, 256, 128, 5, 2, 2, 1] - [16, 24, 512, 96, 7, 1, 3, 1] - [8, 16, 1024, 32, 3, 2, 1, 2] - [4, 8, 2048, 16, 5, 1, 2, 1] conv_transpose2d: shape_desc: N, C_in, H, W, C_out, K_h, K_w, stride, padding, groups shapes: - [1, 64, 128, 128, 64, 3, 3, 1, 1, 1] - [1, 64, 64, 64, 32, 3, 3, 2, 1, 1] - [4, 32, 32, 32, 32, 3, 3, 2, 1, 1] - [8, 16, 64, 64, 16, 5, 5, 2, 2, 1] - [16, 32, 16, 16, 64, 3, 3, 2, 1, 1] - [16, 32, 32, 32, 64, 3, 3, 2, 1, 1] - [32, 64, 32, 32, 32, 3, 3, 1, 0, 1] - [32, 64, 16, 16, 32, 3, 3, 2, 1, 1] copy: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] copy_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] copysign: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] copysign_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] cos: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] cos_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] cosh: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] cosh_: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] cosh_out: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] count_nonzero: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cp_gather_indexer_k_quant_cache: shape_desc: batch_size, seq_len, block_size, head_dim, quant_block_size shapes: - [1, 1, 16, 512, 128] - [1, 2, 16, 512, 128] - [1, 4, 16, 512, 128] - [1, 8, 16, 512, 128] - [1, 16, 16, 512, 128] - [1, 17, 16, 512, 128] - [1, 32, 16, 512, 128] - [1, 64, 16, 512, 128] - [1, 128, 16, 512, 128] - [1, 256, 16, 512, 128] - [1, 512, 16, 512, 128] - [1, 1024, 16, 512, 128] - [1, 2048, 16, 512, 128] - [1, 4096, 16, 512, 128] - [1, 8192, 16, 512, 128] - [1, 16384, 16, 512, 128] - [1, 32768, 16, 512, 128] - [1, 65536, 16, 512, 128] - [2, 1, 16, 512, 128] - [4, 1, 16, 512, 128] - [8, 1, 16, 512, 128] - [16, 1, 16, 512, 128] - [32, 1, 16, 512, 128] - [64, 1, 16, 512, 128] - [128, 1, 16, 512, 128] - [256, 1, 16, 512, 128] - [2, 4096, 16, 512, 128] - [4, 4096, 16, 512, 128] - [8, 4096, 16, 512, 128] - [16, 2048, 16, 512, 128] - [32, 1024, 16, 512, 128] - [64, 512, 16, 512, 128] - [128, 256, 16, 512, 128] - [256, 128, 16, 512, 128] - [1, 8192, 64, 512, 128] - [1, 32768, 64, 512, 128] - [1, 65536, 64, 512, 128] - [16, 2048, 64, 512, 128] - [64, 512, 64, 512, 128] - [256, 128, 64, 512, 128] cross_entropy_loss: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] ctc_loss: shape_desc: T, N, C, S shapes: - [64, 4, 32, 16] - [256, 16, 64, 48] - [512, 32, 64, 48] - [1024, 32, 128, 96] ctc_loss_backward: shape_desc: T, N, C, S shapes: - [64, 4, 32, 16] - [256, 16, 64, 48] - [512, 32, 64, 48] - [1024, 32, 128, 96] cudnn_convolution: shape_desc: batch, input_c, input_h, input_w, out_c, kernel_h, kernel_w, stride, padding, groups shapes: - [32, 64, 128, 128, 32, 3, 3, 1, 2, 1] - [32, 64, 210, 210, 16, 5, 5, 2, 1, 1] - [16, 32, 12, 12, 24, 3, 3, 2, 1, 1] - [16, 32, 24, 24, 24, 3, 3, 2, 2, 2] - [16, 32, 24, 24, 24, 3, 3, 1, 2, 2] cummax: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cummin: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cumprod: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cumprod_: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cumsum: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] cutlass_scaled_mm: shape_desc: M, N, K shapes: - [1, 256, 128] - [1, 16384, 1024] - [1, 24576, 496] - [16, 256, 496] - [16, 16384, 128] - [16, 24576, 4096] - [32, 8192, 4096] - [32, 16384, 4096] - [33, 1024, 1024] - [33, 8192, 128] - [64, 2048, 496] - [64, 16384, 1024] - [100, 8192, 496] - [128, 32768, 4096] - [256, 4096, 4096] - [512, 256, 1024] - [512, 8192, 4096] - [512, 16384, 128] - [512, 24576, 128] dequantize_and_gather_k_cache: shape_desc: M, N shapes: - [1, 512, 128, 512, 448, 64] - [2, 1024, 256, 512, 448, 64] - [4, 2048, 512, 512, 448, 64] - [4, 2048, 2048, 512, 448, 64] - [8, 4096, 1024, 512, 448, 64] dgeglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] diag: shape_desc: M, N shapes: - [64] - [1024] - [64, 64] - [256, 1024] - [1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] diag_embed: shape_desc: M, N shapes: - [4, 4] - [16, 16] - [128, 128] - [256, 256] - [1024, 1024] diagonal_backward: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] diff: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] digamma_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] div_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] div_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] dot: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] dreglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] dropout: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] dropout_backward: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] dswiglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] dunder_ior_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] dunder_ior_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] dunder_or_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] dunder_or_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] einsum: shape_desc: B, M, N, K shapes: - [1, 512, 512, 512] - [1, 1024, 1024, 1024] - [16, 512, 512, 512] elu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] elu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] elu_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] embedding: shape_desc: M, N shapes: - [4, 4] - [16, 16] - [128, 128] - [256, 256] - [1024, 1024] embedding_backward: shape_desc: M, N shapes: - [4, 4] - [16, 16] - [128, 128] - [256, 256] - [1024, 1024] embedding_dense_backward: shape_desc: M, N shapes: - [32, 2048, 128, 8192] - [16, 2048, 256, 16384] - [8, 4096, 256, 32768] eq: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] eq_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] erf: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] erf_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exp: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exp2: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exp2_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exp_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exp_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] expm1: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] expm1_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] expm1_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] exponential_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] eye: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] eye_m: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] feature_dropout: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] feature_dropout_: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fft: shape_desc: M, N shapes: - [128, 64] - [128, 128] - [128, 256] - [128, 512] - [128, 1024] - [256, 64] - [256, 128] - [256, 256] - [256, 512] - [256, 1024] - [512, 64] - [512, 128] - [512, 256] - [512, 512] - [512, 1024] - [1024, 64] - [1024, 128] - [1024, 256] - [1024, 512] - [1024, 1024] - [4096, 64] - [4096, 128] - [4096, 256] - [4096, 512] - [4096, 1024] fill_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fill_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fill_scalar_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fill_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fill_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fill_tensor_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] flash_mla: shape_desc: M, N shapes: - [1024] - [2048] - [4096] - [8192] - [16384] flash_mla_sparse_fwd: shape_desc: s_q, s_kv, topk, h_q, d_qk shapes: - [4096, 8192, 2048, 128, 576] - [4096, 32768, 2048, 128, 576] - [4096, 65536, 2048, 128, 576] - [4096, 98304, 2048, 128, 576] - [4096, 131072, 2048, 128, 576] - [4096, 8192, 512, 64, 512] - [4096, 32768, 512, 64, 512] - [4096, 49152, 512, 64, 512] - [4096, 65536, 512, 64, 512] - [4096, 8192, 1024, 128, 512] - [4096, 32768, 1024, 128, 512] - [4096, 49152, 1024, 128, 512] - [4096, 65536, 1024, 128, 512] flip: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] float_power_: shape_desc: (B), M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 65536] floor: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] floor_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] floor_divide_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] floor_divide_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] floor_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] fmin: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] fmin_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fmod_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] fmod_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fmod_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fmod_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fmod_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fp8_einsum: shape_desc: M, N shapes: - [1, 8, 4096, 1024] - [4, 8, 4096, 1024] - [8, 8, 4096, 1024] - [16, 8, 4096, 1024] - [32, 8, 4096, 1024] - [64, 8, 4096, 1024] - [128, 8, 4096, 1024] - [4096, 8, 4096, 1024] - [8192, 8, 4096, 1024] - [16384, 8, 4096, 1024] - [32768, 8, 4096, 1024] - [1, 16, 7168, 1024] - [4, 16, 7168, 1024] - [8, 16, 7168, 1024] - [16, 16, 7168, 1024] - [32, 16, 7168, 1024] - [64, 16, 7168, 1024] - [128, 16, 7168, 1024] - [4096, 16, 7168, 1024] - [8192, 16, 7168, 1024] - [16384, 16, 7168, 1024] - [32768, 16, 7168, 1024] fp8_paged_mqa_logits_gems_vs_deepgemm: shape_desc: batch_size, next_n, heads, head_dim, avg_kv shapes: - [1, 1, 16, 64, 1024] - [2, 1, 32, 128, 2048] - [4, 1, 32, 128, 2048] - [2, 2, 32, 128, 2048] - [8, 1, 32, 128, 3072] full: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] full_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] functional_sym_constrain_range_for_size: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fused_add_rms_norm: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert: shape_desc: num_tokens, num_heads, num_tokens_insert, block_size, max_pos, eps shapes: - [1, 64, 1, 64, 4096, 1.0e-06] - [1, 128, 1, 64, 4096, 1.0e-06] - [4, 64, 4, 64, 4096, 1.0e-06] - [4, 128, 4, 64, 4096, 1.0e-06] - [17, 64, 17, 64, 4096, 1.0e-06] - [17, 128, 17, 64, 4096, 1.0e-06] - [64, 64, 64, 64, 4096, 1.0e-06] - [64, 128, 64, 64, 4096, 1.0e-06] - [1024, 64, 1024, 64, 4096, 1.0e-06] - [1024, 128, 1024, 64, 4096, 1.0e-06] - [2048, 64, 2048, 64, 4096, 1.0e-06] - [2048, 128, 2048, 64, 4096, 1.0e-06] - [8192, 64, 8192, 64, 4096, 1.0e-06] - [8192, 128, 8192, 64, 4096, 1.0e-06] - [32768, 64, 32768, 64, 4096, 1.0e-06] - [32768, 128, 32768, 64, 4096, 1.0e-06] - [65536, 64, 65536, 64, 4096, 1.0e-06] - [65536, 128, 65536, 64, 4096, 1.0e-06] - [98304, 64, 98304, 64, 4096, 1.0e-06] - [98304, 128, 98304, 64, 4096, 1.0e-06] - [131072, 64, 131072, 64, 4096, 1.0e-06] - [131072, 128, 131072, 64, 4096, 1.0e-06] fused_experts_impl: shape_desc: num_tokens, num_experts, hidden_size, intermediate_size, topk shapes: - [1, 8, 4096, 14336, 2] - [4, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [128, 8, 4096, 14336, 2] - [256, 8, 4096, 14336, 2] - [512, 8, 4096, 14336, 2] - [1, 256, 7168, 2048, 8] - [4, 256, 7168, 2048, 8] - [16, 256, 7168, 2048, 8] - [64, 256, 7168, 2048, 8] - [128, 256, 7168, 2048, 8] - [256, 256, 7168, 2048, 8] - [1, 512, 4096, 1024, 10] - [4, 512, 4096, 1024, 10] - [16, 512, 4096, 1024, 10] - [64, 512, 4096, 1024, 10] - [128, 512, 4096, 1024, 10] - [256, 512, 4096, 1024, 10] fused_inv_rope_fp8_quant: shape_desc: num_tokens, num_heads, n_groups, tma_aligned_scales shapes: - [256, 128, 8, false] - [512, 128, 8, false] - [1024, 128, 8, false] - [2048, 128, 8, false] - [4096, 128, 8, false] - [256, 128, 8, true] - [512, 128, 8, true] - [1024, 128, 8, true] - [2048, 128, 8, true] - [4096, 128, 8, true] fused_marlin_moe: shape_desc: M, N shapes: - [1, 8, 4096, 14336, 2] - [4, 8, 4096, 14336, 2] - [8, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [32, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [128, 8, 4096, 14336, 2] - [256, 8, 4096, 14336, 2] - [1, 256, 7168, 2048, 8] - [4, 256, 7168, 2048, 8] - [8, 256, 7168, 2048, 8] - [16, 256, 7168, 2048, 8] - [32, 256, 7168, 2048, 8] - [64, 256, 7168, 2048, 8] - [128, 256, 7168, 2048, 8] - [256, 256, 7168, 2048, 8] - [1, 512, 4096, 1024, 10] - [4, 512, 4096, 1024, 10] - [8, 512, 4096, 1024, 10] - [16, 512, 4096, 1024, 10] - [32, 512, 4096, 1024, 10] - [64, 512, 4096, 1024, 10] - [128, 512, 4096, 1024, 10] - [256, 512, 4096, 1024, 10] - [1, 256, 4096, 2048, 6] - [4, 256, 4096, 2048, 6] - [8, 256, 4096, 2048, 6] - [16, 256, 4096, 2048, 6] - [32, 256, 4096, 2048, 6] - [64, 256, 4096, 2048, 6] - [128, 256, 4096, 2048, 6] - [256, 256, 4096, 2048, 6] fused_marlin_moe_int8: shape_desc: M, N shapes: - [1, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [1, 256, 7168, 2048, 8] - [16, 256, 7168, 2048, 8] - [64, 256, 7168, 2048, 8] fused_moe: shape_desc: M, N shapes: - [1, 8, 4096, 14336, 2] - [4, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [128, 8, 4096, 14336, 2] - [256, 8, 4096, 14336, 2] - [512, 8, 4096, 14336, 2] - [1, 64, 7168, 2048, 8] - [4, 64, 7168, 2048, 8] - [16, 64, 7168, 2048, 8] - [64, 64, 7168, 2048, 8] - [128, 64, 7168, 2048, 8] - [256, 64, 7168, 2048, 8] - [1, 128, 4096, 1024, 10] - [4, 128, 4096, 1024, 10] - [16, 128, 4096, 1024, 10] - [64, 128, 4096, 1024, 10] - [128, 128, 4096, 1024, 10] - [256, 128, 4096, 1024, 10] fused_moe_int8_w8a16_gems_vs_bf16_deq: shape_desc: M, N shapes: - [1, 8, 4096, 14336, 2] - [4, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [128, 8, 4096, 14336, 2] - [256, 8, 4096, 14336, 2] - [512, 8, 4096, 14336, 2] - [1, 256, 7168, 2048, 8] - [4, 256, 7168, 2048, 8] - [16, 256, 7168, 2048, 8] - [64, 256, 7168, 2048, 8] - [128, 256, 7168, 2048, 8] - [256, 256, 7168, 2048, 8] fused_q_kv_rmsnorm: shape_desc: M, N shapes: - [1, 1536, 512] - [32, 1536, 512] - [128, 1536, 512] - [512, 1536, 512] - [2048, 1536, 512] - [32, 36864, 576] - [128, 36864, 576] gather: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] gather_backward: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] gcd: shape_desc: (B), M, N shapes: - [65536] - [1024, 1024] - [256, 4096] - [64, 256, 256] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] gcd_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] ge: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] ge_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] geglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] gelu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] gelu_and_mul: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] gelu_backward: shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [256, 1024, 1024] glu: shape_desc: M, N shapes: - [4, 8, 512, 128] - [4, 8, 1024, 128] - [4, 8, 2048, 128] - [4, 8, 3072, 128] - [4, 8, 4096, 128] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] glu_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] greater: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] greater_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] greater_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] greater_scalar_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] grid_sample: shape_desc: M, N shapes: - [1, 3, 32, 32] - [2, 16, 32, 32] - [1, 3, 8, 8, 8] - [2, 4, 8, 8, 8] - [2, 32, 64, 64] - [4, 64, 64, 64] - [2, 8, 16, 16, 16] - [2, 16, 16, 16, 16] - [4, 128, 128, 128] - [2, 32, 32, 32, 32] group_norm: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] grouped_mm: shape_desc: Groups, N, K shapes: - [16, 512, 2048] - [16, 2560, 2048] - [64, 2048, 128] grouped_topk: shape_desc: M, N shapes: - [1, 64, 8, 2, 8] - [8, 64, 8, 2, 8] - [32, 64, 8, 2, 8] - [64, 64, 8, 2, 8] - [128, 64, 8, 2, 8] - [256, 64, 8, 2, 8] - [32, 128, 8, 2, 8] - [64, 128, 8, 2, 8] - [128, 128, 8, 2, 8] - [64, 64, 4, 2, 4] - [64, 128, 16, 2, 8] - [512, 64, 8, 2, 8] - [1024, 64, 8, 2, 8] - [2048, 64, 8, 2, 8] groupmm: shape_desc: Groups, N, K shapes: - [16, 512, 2048] - [16, 2560, 2048] - [64, 2048, 128] gt: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] gt_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] hadamard_transform: shape_desc: batch, dim shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] hadamard_transform_mn: shape_desc: batch, dim shapes: - [1024, 1536] - [1024, 3072] - [1024, 6144] - [1024, 12288] - [8192, 1536] - [8192, 3072] - [8192, 6144] - [8192, 12288] - [32768, 1536] - [32768, 3072] - [32768, 6144] - [32768, 12288] - [1024, 10240] - [1024, 14336] - [1024, 20480] - [8192, 10240] - [8192, 14336] - [8192, 20480] - [1024, 40960] - [8192, 40960] hardsigmoid: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] hardswish_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] hc_head_fused_kernel: shape_desc: N, hidden_size shapes: - [1, 1280, 4] - [4, 2560, 4] - [16, 4096, 4] - [64, 7168, 4] - [256, 1280, 2] - [256, 1280, 4] - [512, 1280, 2] - [512, 1280, 4] - [512, 2560, 2] - [512, 2560, 4] - [1024, 2560, 2] - [1024, 2560, 4] - [2048, 4096, 2] - [2048, 4096, 4] - [4096, 4096, 2] - [4096, 4096, 4] hc_split_sinkhorn_forward: shape_desc: batch, seqlen shapes: - [8, 16, 4] - [32, 64, 4] - [128, 128, 4] - [256, 256, 4] - [8, 16, 2] - [32, 64, 2] - [128, 128, 2] - [256, 256, 2] histc: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] hstack: shapes: - [536870912] - [64, 64] - [4096, 4096] - [64, 512, 512] - [512, 512, 512] huber_loss: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [2048, 32768] - [2048, 65536] - [4096, 32768] - [4096, 65536] - [3072, 49152] - [3072, 65536] hypot: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] hypot_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] i0: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] i0_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] i0_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] index: shape_desc: M, N shapes: - - [268435456] - - [65536] - - [32, 32] - - [8] - [8] - - [32, 32] - - [8] - [2, 8] - - [32, 32] - - [2, 8] - - [1024, 1024] - - [64] - [64] - - [512, 512, 512] - - [128] - [128] - [128] - - [512, 512, 512] - - [2, 128] - [2, 128] - [2, 128] - - [512, 512, 512] - - [2, 128] - [128] - [128] - - [512, 512, 512] - - [2, 128] - - [64, 64, 64] - - [2, 8] - [2, 8] index_add: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] index_add_: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] index_copy: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1, 2] - [4096, 256] - [200, 40999, 3] index_copy_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1, 2] - [4096, 256] - [200, 40999, 3] index_put: shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate shapes: - - [268435456] - - [65536] - [65536] - false - - [32, 32] - - [8] - [8] - [8] - false - - [32, 32] - - [8] - [2, 8] - [8] - false - - [32, 32] - - [2, 8] - [32] - false - - [1024, 1024] - - [64] - [64] - [64] - false - - [1024, 1024] - - [64] - [4, 64] - [64] - false - - [1024, 1024] - - [4, 64] - [1024] - false - - [512, 512, 512] - - [128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [512] - false - - [100] - - [100] - [100] - true - - [32, 32] - - [32, 32] - [32, 32] - true - - [16, 16, 4] - - [16, 16, 4] - [16, 16, 4] - true - - [1024, 1024] - - [1024, 1024] - [1048576] - true - - [512, 512, 512] - - [2, 128] - [2, 128] - [2, 128] - [2, 128] - false - - [512, 512] - - [512, 512] - [262144] - true - - [64, 64, 64] - - [64, 64, 64] - [262144] - true index_put_: shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate shapes: - - [268435456] - - [65536] - [65536] - false - - [32, 32] - - [8] - [8] - [8] - false - - [32, 32] - - [8] - [2, 8] - [8] - false - - [32, 32] - - [2, 8] - [32] - false - - [1024, 1024] - - [64] - [64] - [64] - false - - [1024, 1024] - - [64] - [4, 64] - [64] - false - - [1024, 1024] - - [4, 64] - [1024] - false - - [512, 512, 512] - - [128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [512] - false - - [100] - - [100] - [100] - true - - [32, 32] - - [32, 32] - [32, 32] - true - - [16, 16, 4] - - [16, 16, 4] - [16, 16, 4] - true - - [1024, 1024] - - [1024, 1024] - [1048576] - true - - [512, 512, 512] - - [2, 128] - [2, 128] - [2, 128] - [2, 128] - false - - [512, 512] - - [512, 512] - [262144] - true - - [64, 64, 64] - - [64, 64, 64] - [262144] - true index_put_impl: shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate shapes: - - [268435456] - - [65536] - [65536] - false - - [32, 32] - - [8] - [8] - [8] - false - - [32, 32] - - [8] - [2, 8] - [8] - false - - [32, 32] - - [2, 8] - [32] - false - - [1024, 1024] - - [64] - [64] - [64] - false - - [1024, 1024] - - [64] - [4, 64] - [64] - false - - [1024, 1024] - - [4, 64] - [1024] - false - - [512, 512, 512] - - [128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [128] - [128] - [128] - false - - [512, 512, 512] - - [2, 128] - [512] - false - - [100] - - [100] - [100] - true - - [32, 32] - - [32, 32] - [32, 32] - true - - [16, 16, 4] - - [16, 16, 4] - [16, 16, 4] - true - - [1024, 1024] - - [1024, 1024] - [1048576] - true - - [512, 512, 512] - - [2, 128] - [2, 128] - [2, 128] - [2, 128] - false - - [512, 512] - - [512, 512] - [262144] - true - - [64, 64, 64] - - [64, 64, 64] - [262144] - true index_select: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] index_select_backward: shape_desc: N, M shapes: - [16, 64] - [32, 128] - [64, 256] - [16, 16, 64] - [32, 32, 128] indexer_k_quant_and_cache: shape_desc: num_tokens, num_blocks, block_size, head_dim, quant_block_size shapes: - [1, 1, 16, 512, 128] - [2, 1, 16, 512, 128] - [4, 1, 16, 512, 128] - [8, 1, 16, 512, 128] - [16, 2, 16, 512, 128] - [17, 3, 16, 512, 128] - [32, 4, 16, 512, 128] - [64, 8, 16, 512, 128] - [128, 16, 16, 512, 128] - [256, 32, 16, 512, 128] - [512, 64, 16, 512, 128] - [1024, 128, 16, 512, 128] - [2048, 256, 16, 512, 128] - [4096, 512, 16, 512, 128] - [8192, 1024, 16, 512, 128] - [16384, 2048, 16, 512, 128] - [32768, 4096, 16, 512, 128] - [65536, 8192, 16, 512, 128] - [8192, 256, 64, 512, 128] - [32768, 1024, 64, 512, 128] - [65536, 2048, 64, 512, 128] inplace_fused_experts: shape_desc: M, N shapes: - [1, 8, 4096, 14336, 2] - [4, 8, 4096, 14336, 2] - [16, 8, 4096, 14336, 2] - [64, 8, 4096, 14336, 2] - [128, 8, 4096, 14336, 2] - [256, 8, 4096, 14336, 2] - [512, 8, 4096, 14336, 2] - [1, 256, 7168, 2048, 8] - [4, 256, 7168, 2048, 8] - [16, 256, 7168, 2048, 8] - [64, 256, 7168, 2048, 8] - [128, 256, 7168, 2048, 8] - [256, 256, 7168, 2048, 8] instance_norm: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] is_all_true: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] isclose: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] isfinite: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] isin: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] isin_scalar_tensor: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] isin_tensor_scalar: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] isinf: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] isnan: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] isneginf: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] kron: shape_desc: M, N shapes: - [16, 16] - [64, 64] - [128, 128] - [256, 256] - [4, 8, 16, 32] layer_norm: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] layer_norm_backward: shape_desc: N, C, * shapes: - [4, 16, 64, 4] - [16, 16, 8, 48] - [16, 16, 8, 88] - [16, 16, 128] - [20, 6, 65536] - [16, 16, 64] - [16, 16, 1024] - [16, 16, 4098] - [1, 8, 4, 4] - [16, 8, 128, 128] le: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] le_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] leaky_relu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] leaky_relu_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] lerp_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] lerp_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] lerp_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] lerp_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] lift_fresh_copy: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] linspace: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] log: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log10: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log10_: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log10_out: shape_desc: (B), M, N shapes: - [4096, 4096] - [64, 512, 512] - [1024, 65536] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log1p: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log1p_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log_sigmoid: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] log_softmax: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] log_softmax_backward_data: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] log_softmax_backward_data_out: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] log_softmax_out: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] logaddexp: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logaddexp_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] logical_and: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logical_and_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logical_not: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] logical_or: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logical_or_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logical_xor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] logit: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] logit_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] logspace: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] logsumexp: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] lt: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] lt_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] margin_ranking_loss: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1048576] - [1024, 1] - [1024, 256] - [1024, 4096] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] masked_fill: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] masked_fill_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] masked_fill_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] masked_fill_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] masked_scatter: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] masked_scatter_: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] masked_select: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] max: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] max_dim: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] max_pool2d_backward: shape_desc: N, C, H, W shapes: - [4, 3, 224, 224] - [16, 64, 56, 56] - [32, 128, 28, 28] - [64, 256, 14, 14] - [128, 512, 7, 7] max_pool2d_with_indices: shape_desc: N, C, H, W shapes: - [4, 3, 224, 224] - [16, 64, 56, 56] - [32, 128, 28, 28] - [64, 256, 14, 14] - [128, 512, 7, 7] max_pool3d: shape_desc: N, C, D, H, W shapes: - [4, 3, 16, 56, 56] - [8, 64, 8, 28, 28] - [16, 128, 4, 14, 14] - [32, 256, 2, 7, 7] max_pool3d_backward: shape_desc: N, C, D, H, W shapes: - [4, 3, 16, 56, 56] - [8, 64, 8, 28, 28] - [16, 128, 4, 14, 14] - [32, 256, 2, 7, 7] maximum: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] mean: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] mean_dim: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] median: shape_desc: input shape shapes: - [2] - [64] - [65] - [128] - [256] - [257] - [1024] - [4096] - [4, 8, 16, 8] median_dim: shape_desc: input shape or [input shape, dim, keepdim] shapes: - [1536, 640] - [144, 8192] - [768, 1536] - [32, 384, 128] - - [32, 384, 128] - 1 - false - - [640, 1536] - 0 - false - - [8, 64, 384, 64] - 2 - false mhc_bwd: shape_desc: seqlen, n_stream shapes: - [256, 4] - [1024, 4] - [4096, 4] - [8192, 4] - [16384, 4] - [65536, 4] mhc_post: shape_desc: N, H shapes: - [4096, 1280] - [4096, 2560] - [4096, 7168] mhc_pre: shape_desc: N, hidden_size shapes: - [512, 1280] - [512, 2560] - [512, 4096] - [1024, 1280] - [1024, 2560] - [1024, 4096] - [2048, 1280] - [2048, 2560] - [2048, 4096] - [8192, 1280] - [8192, 2560] - [8192, 4096] min: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] min_dim: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] minimum: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] mm: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] mm_out: shape_desc: B, M, N, K shapes: - [2, 384, 384, 384] - [2, 4096, 4096, 4096] - [16, 1024, 1024, 1024] - [16, 2048, 2048, 2048] - [16, 4096, 4096, 4096] - [8, 1848, 1536, 151936] - [8, 1848, 1536, 128256] - [8, 1848, 1536, 152064] - [8, 4096, 1, 152064] - [4, 1, 1024, 4096] - [4, 1, 128256, 4096] - [4, 1, 14336, 4096] - [4, 1, 4096, 14336] - [4, 1, 4096, 4096] - [4, 1, 6144, 4096] - [4, 1, 28672, 4096] - [4, 1, 3584, 3584] - [4, 1, 18944, 3584] - [4, 1, 3584, 18944] - [4, 1, 152064, 3584] - [4, 1, 37888, 3584] - [4, 1, 512, 3584] - [4, 1, 4608, 3584] - [4, 2, 1024, 4096] - [4, 2, 128256, 4096] - [4, 2, 14336, 4096] - [4, 2, 4096, 14336] - [4, 2, 4096, 4096] - [4, 2, 6144, 4096] - [4, 2, 28672, 4096] - [4, 2, 3584, 3584] - [4, 2, 18944, 3584] - [4, 2, 3584, 18944] - [4, 2, 152064, 3584] - [4, 2, 37888, 3584] - [4, 2, 512, 3584] - [4, 2, 4608, 3584] - [4, 3, 1024, 4096] - [4, 3, 128256, 4096] - [4, 3, 14336, 4096] - [4, 3, 4096, 14336] - [4, 3, 4096, 4096] - [4, 3, 6144, 4096] - [4, 3, 28672, 4096] - [4, 3, 3584, 3584] - [4, 3, 18944, 3584] - [4, 3, 3584, 18944] - [4, 3, 152064, 3584] - [4, 3, 37888, 3584] - [4, 3, 512, 3584] - [4, 3, 4608, 3584] - [4, 4, 1024, 4096] - [4, 4, 128256, 4096] - [4, 4, 14336, 4096] - [4, 4, 4096, 14336] - [4, 4, 4096, 4096] - [4, 4, 6144, 4096] - [4, 4, 28672, 4096] - [4, 4, 3584, 3584] - [4, 4, 18944, 3584] - [4, 4, 3584, 18944] - [4, 4, 152064, 3584] - [4, 4, 37888, 3584] - [4, 4, 512, 3584] - [4, 4, 4608, 3584] - [4, 8, 1024, 4096] - [4, 8, 128256, 4096] - [4, 8, 14336, 4096] - [4, 8, 4096, 14336] - [4, 8, 4096, 4096] - [4, 8, 6144, 4096] - [4, 8, 28672, 4096] - [4, 8, 3584, 3584] - [4, 8, 18944, 3584] - [4, 8, 3584, 18944] - [4, 8, 152064, 3584] - [4, 8, 37888, 3584] - [4, 8, 512, 3584] - [4, 8, 4608, 3584] - [4, 98, 1024, 4096] - [4, 98, 128256, 4096] - [4, 98, 14336, 4096] - [4, 98, 4096, 14336] - [4, 98, 4096, 4096] - [4, 98, 6144, 4096] - [4, 98, 28672, 4096] - [4, 98, 3584, 3584] - [4, 98, 18944, 3584] - [4, 98, 3584, 18944] - [4, 98, 152064, 3584] - [4, 98, 37888, 3584] - [4, 98, 512, 3584] - [4, 98, 4608, 3584] - [4, 256, 1024, 4096] - [4, 256, 128256, 4096] - [4, 256, 14336, 4096] - [4, 256, 4096, 14336] - [4, 256, 4096, 4096] - [4, 256, 6144, 4096] - [4, 256, 28672, 4096] - [4, 256, 3584, 3584] - [4, 256, 18944, 3584] - [4, 256, 3584, 18944] - [4, 256, 152064, 3584] - [4, 256, 37888, 3584] - [4, 256, 512, 3584] - [4, 256, 4608, 3584] - [4, 8192, 1024, 4096] - [4, 8192, 128256, 4096] - [4, 8192, 14336, 4096] - [4, 8192, 4096, 14336] - [4, 8192, 4096, 4096] - [4, 8192, 6144, 4096] - [4, 8192, 28672, 4096] - [4, 8192, 3584, 3584] - [4, 8192, 18944, 3584] - [4, 8192, 3584, 18944] - [4, 8192, 152064, 3584] - [4, 8192, 37888, 3584] - [4, 8192, 512, 3584] - [4, 8192, 4608, 3584] mm_self_transpose: shape_desc: M, K shapes: - [257, 96] - [384, 384] - [1536, 320] - [3072, 768] - [1024, 1024] - [4096, 1024] - [5333, 71] - [8192, 2048] - [10240, 4096] moe_align_block_size_triton: shape_desc: M, N shapes: - [512, 64, 16384, 10] - [512, 64, 6152, 10] - [512, 64, 4727, 10] - [512, 64, 1905, 10] - [512, 64, 11575, 10] - [512, 64, 1032, 10] - [512, 64, 4201, 10] - [512, 64, 2056, 10] - [512, 64, 7561, 10] - [512, 64, 4104, 10] - [512, 64, 14281, 10] moe_sum: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] mse_loss: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] mul: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] mul_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] multinomial: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] mv: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] nan_to_num: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] nanmedian: shape_desc: N or M, N shapes: - [64] - [64, 64] - [1024, 1024] - [256, 4096] - [16, 131072] nanmedian_dim: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [256, 4096] - [16, 131072] nanmedian_dim_values: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [256, 4096] - [16, 131072] nanmedian_out: shape_desc: N or M, N shapes: - [64] - [64, 64] - [1024, 1024] - [256, 4096] - [16, 131072] ne: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] ne_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] neg: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] neg_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] new_full: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] nll_loss2d_backward: shape_desc: M, N shapes: - [64, 64, 4, 8] - [256, 256, 4, 8] - [1024, 1024, 4, 8] - [4096, 4096, 4, 8] - [1024, 65536, 4, 8] nll_loss2d_forward: shape_desc: M, N shapes: - [64, 64, 4, 8] - [256, 256, 4, 8] - [1024, 1024, 4, 8] - [4096, 4096, 4, 8] - [1024, 65536, 4, 8] nll_loss_backward: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] nll_loss_forward: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] nll_loss_nd_backward: shape_desc: N, C, d1, d2, ... shapes: - [64, 64] - [256, 256] - [10000, 65536] - [32, 128, 512] - [64, 64, 4, 8] - [256, 256, 4, 8] - [4096, 4096, 4, 8] - [64, 64, 8, 4, 8] nll_loss_nd_forward: shape_desc: N, C, d1, d2, ... shapes: - [64, 64] - [256, 256] - [10000, 65536] - [32, 128, 512] - [64, 64, 4, 8] - [256, 256, 4, 8] - [4096, 4096, 4, 8] - [64, 64, 8, 4, 8] nonzero: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] nonzero_numpy: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] normal_float_float_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] normal_float_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] normal_tensor_float: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] normal_tensor_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] one_hot: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] ones: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] ones_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] outer: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] pack_seq_triton: shape_desc: N, D, B, lengths shapes: - - 512 - 64 - 5 - [64, 128, 64, 128, 128] - - 4096 - 128 - 4 - [1024, 1024, 1024, 1024] - - 8192 - 256 - 5 - [1024, 2048, 1024, 2048, 2048] - - 2048 - 512 - 4 - [512, 512, 512, 512] - - 16384 - 64 - 8 - [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] - - 1024 - 1024 - 4 - [256, 256, 256, 256] pad: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] per_token_group_quant_fp8: shape_desc: M, N shapes: - [7, 512, 512] - [7, 4096, 256] - [83, 512, 64] - [2048, 4096, 256] - [2048, 13824, 512] pixel_shuffle: shape_desc: N, C, H, W, upscale_factor shapes: - [1, 4, 2, 3, 2] - [2, 9, 4, 4, 3] - [4, 64, 32, 32, 2] - [2, 128, 64, 64, 2] - [1, 64, 16, 16, 4] - [8, 36, 64, 64, 3] - [1, 16, 128, 128, 2] pixel_unshuffle: shape_desc: M, N shapes: - - [1, 3, 8, 8] - 2 - - [2, 4, 12, 6] - 3 - - [4, 16, 64, 48] - 4 poisson: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] polar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] pow_tensor_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] pow_tensor_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] prelu: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] prod: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] quantile: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 256] - [64, 512, 128] - [20, 8, 10000] - [4] - [1024] - [65535] - [1024, 1] - [1024, 8] - [1024, 64] - [1024, 512] - [1024, 4096] - [64, 64, 1] - [64, 64, 8] - [64, 64, 64] - [64, 64, 512] - [64, 64, 4096] rad2deg: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] rad2deg_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] rand: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] rand_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] randint: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 512] - [16, 131072] - [8, 262144] randint_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] randn: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] randn_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] randperm: shape_desc: M shapes: - [64] - [1024] - [2048] - [4096] - [65536] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] reciprocal: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] reciprocal_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] reflection_pad1d: shape_desc: M, N shapes: - - [3, 33] - [1, 1] - - [2, 4, 64] - [3, 5] - - [8, 16, 256] - [8, 8] - - [32, 64, 2048] - [3, 5] reflection_pad1d_backward: shape_desc: M, N shapes: - [2, 3] - [4, 8] - [8, 16] - [1, 32] - [4, 64] - [8, 128] reflection_pad1d_out: shape_desc: M, N shapes: - - [3, 33] - [1, 1] - - [2, 4, 64] - [3, 5] - - [8, 16, 256] - [8, 8] - - [32, 64, 2048] - [3, 5] reflection_pad2d: shape_desc: M, N shapes: - - [3, 33, 33] - [1, 1, 1, 1] - - [2, 4, 32, 64] - [2, 3, 2, 3] - - [8, 16, 64, 64] - [3, 5, 3, 5] - - [32, 64, 128, 256] - [0, 4, 0, 4] - - [16, 32, 64, 128] - [1, 1, 1, 1] reflection_pad2d_out: shape_desc: M, N shapes: - - [3, 33, 33] - [1, 1, 1, 1] - - [2, 4, 32, 64] - [2, 3, 2, 3] - - [8, 16, 64, 64] - [3, 5, 3, 5] - - [32, 64, 128, 256] - [0, 4, 0, 4] - - [16, 32, 64, 128] - [1, 1, 1, 1] reglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] relu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] relu6: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] relu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] remainder: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] remainder_scalar_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] remainder_scalar_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] remainder_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] remainder_tensor_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] renorm: shape_desc: M, N shapes: - [4, 8] - [8, 16] - [16, 32] - [32, 64] - [64, 128] - [128, 256] - [16, 32, 64] - [8, 16, 128] repeat: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [16, 256, 256] - [512, 512, 512] - [64, 64, 64, 64] repeat_interleave_self_int: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [16, 256, 256] - [512, 512, 512] - [64, 64, 64, 64] repeat_interleave_self_tensor: shape_desc: M, N, K shapes: - [16, 256, 256] - [128, 256, 256] - [64, 64, 64, 64] repeat_interleave_tensor: shape_desc: M, N, K shapes: - [16, 256, 256] - [128, 256, 256] - [64, 64, 64, 64] replication_pad1d: shape_desc: M, N shapes: - - [2, 3, 7] - [1, 2] - - [4, 16, 64] - [3, 1] - - [8, 32, 256] - [1, 2] - - [32, 256] - [3, 1] replication_pad3d: shape_desc: M, N shapes: - [1, 3, 16, 256, 256] - [4, 16, 32, 64, 64] - [8, 64, 8, 32, 32] - [2, 32, 16, 128, 128] - [1, 1, 64, 128, 128] reshape_and_cache: shape_desc: M, N shapes: - [21, 4, 64, 8, 512] - [42, 8, 64, 8, 1024] - [42, 8, 80, 16, 10000] - [42, 8, 120, 32, 10000] - [42, 8, 256, 8, 1024] reshape_and_cache_flash: shape_desc: M, N shapes: - [21, 4, 64, 8, 512] - [21, 4, 64, 8, 1024] - [21, 4, 80, 16, 10000] - [42, 8, 64, 8, 1024] - [42, 8, 80, 16, 10000] resolve_conj: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] resolve_neg: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] rms_norm: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] roll: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] rot90: shape_desc: M, N shapes: - [64, 64] - [128, 128] - [256, 256] - [512, 512] - [1024, 1024] - [2048, 2048] - [100, 200] - [200, 400] - [400, 800] round: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] round_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] round_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] router_gemm: shape_desc: M, N, K shapes: - [1, 8, 4096] - [16, 8, 4096] - [64, 8, 4096] - [256, 8, 4096] - [1024, 8, 4096] - [4096, 8, 4096] - [64, 64, 7168] - [256, 64, 7168] - [1024, 128, 7168] - [4096, 128, 7168] rrelu_with_noise_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] rsqrt: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] rsqrt_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] rsub_scalar: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] rsub_tensor: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] rwkv_ka_fusion: shape_desc: M, N shapes: - [64] - [256] - [1024] - [4096] - [8192] - [16384] - [32768] rwkv_mm_sparsity: shape_desc: M, N shapes: - [1] safe_softmax: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] scaled_dot_product_attention: shape_desc: M, N shapes: - [4, 32, 1024, 64] - [4, 32, 1024, 128] - [4, 32, 2048, 128] - [4, 32, 4096, 128] - [4, 32, 8192, 128] scaled_mm: shape_desc: M, N, K shapes: - [16, 16, 16] - [128, 128, 128] - [512, 512, 512] scaled_mm_out: shape_desc: M, N, K shapes: - [16, 16, 16] - [128, 128, 128] - [512, 512, 512] scaled_softmax_backward: shape_desc: batch, heads, query_len, key_len shapes: - [1, 4, 64, 64] - [2, 8, 128, 128] - [4, 8, 256, 256] - [8, 12, 512, 512] - [16, 16, 1024, 1024] - [32, 16, 512, 512] - [1, 32, 2048, 2048] - [2, 40, 4096, 4096] scaled_softmax_forward: shape_desc: batch, heads, query_len, key_len shapes: - [1, 4, 64, 64] - [2, 8, 128, 128] - [4, 8, 256, 256] - [8, 12, 512, 512] - [16, 16, 1024, 1024] - [32, 16, 512, 512] - [1, 32, 2048, 2048] - [2, 40, 4096, 4096] scatter_add_: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] scatter_reduce.two: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] scatter_src: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] scatter_src_: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] searchsorted: shape_desc: sorted_sequence shape, values shape, sorter, right, out_int32 shapes: - - [1024] - [4096] - false - false - false - - [64, 256] - [64, 256] - false - true - false - - [256, 1024] - [256, 512] - false - false - true searchsorted_out: shape_desc: sorted_sequence shape, values shape, sorter, right, out_int32 shapes: - - [1024] - [4096] - false - false - false - - [64, 256] - [64, 256] - false - true - false - - [256, 1024] - [256, 512] - false - false - true searchsorted_scalar: shape_desc: sorted_sequence shape, right, out_int32 shapes: - - [1024] - false - false - - [4096] - true - false - - [8192] - false - true searchsorted_scalar_out: shape_desc: sorted_sequence shape, right, out_int32 shapes: - - [1024] - false - false - - [4096] - true - false - - [8192] - false - true segment_reduce: shape_desc: data shape shapes: &id001 - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] segment_reduce_backward: shape_desc: data shape shapes: *id001 segment_reduce_backward_out: shape_desc: data shape shapes: *id001 segment_reduce_out: shape_desc: data shape shapes: *id001 select_backward: shape_desc: M, N shapes: - [128, 256] - [1024, 1024] - [512, 1024, 512] - [16, 8192, 4096] - [8, 4096, 11008] - [4, 32, 4096, 128] - [32, 256, 256, 128] select_scatter: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] selu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] selu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sgn_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sigmoid: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sigmoid_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sigmoid_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] signbit: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] silu: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] silu_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] silu_and_mul: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] silu_and_mul_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] silu_and_mul_with_clamp: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] silu_and_mul_with_clamp_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] silu_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sin: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sin_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] single_dim_shapes: shape_desc: M shapes: - [64] - [1024] - [2048] - [4096] - [65536] sinh_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] skip_layer_norm: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] slice_backward: shape_desc: M, N shapes: - [128, 256] - [1024, 1024] - [512, 1024, 512] - [16, 8192, 4096] - [8, 4096, 11008] - [4, 32, 4096, 128] - [32, 256, 256, 128] slice_scatter: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 256] - [10000, 65536] smooth_l1_loss: shape_desc: (B), M, N shapes: - [262144] - [1024, 1024] - [4096, 4096] - [64, 512, 512] smooth_l1_loss_backward: shape_desc: (B), M, N shapes: - [262144] - [1024, 1024] - [4096, 4096] - [64, 512, 512] soft_margin_loss: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] softmax: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] softmax_backward: shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [256, 1024, 1024] softmax_backward_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] softmax_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] softplus: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] softshrink: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] softshrink_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sort: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [1024, 1] - [1024, 512] - [16, 131072] - [8, 262144] sort_stable: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [1024, 1] - [1024, 512] - [16, 131072] - [8, 262144] sparse_attention: shape_desc: B, M, KV_LEN, TOPK, H, D shapes: - [16, 1, 136, 136, 8, 512] - [16, 1, 392, 385, 8, 512] - [16, 1, 392, 386, 8, 512] - [16, 1, 392, 387, 8, 512] - [32, 1, 392, 388, 8, 512] - [32, 1, 392, 389, 8, 512] - [32, 1, 392, 390, 8, 512] - [32, 1, 392, 391, 8, 512] - [64, 1, 136, 136, 8, 512] - [64, 1, 392, 385, 8, 512] - [64, 1, 392, 388, 8, 512] - [64, 1, 392, 389, 8, 512] special_i0e: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] special_i0e_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] special_i1: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] special_i1_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] split_with_sizes_copy: shape_desc: M, N shapes: - [10] - [10, 4] - [10, 4, 8] - [10, 4, 8, 16] - [16, 32] - [8, 64, 128] - [1, 8192] - [32, 50257] sqrt: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] sqrt_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] square: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] square_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] square_out: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] stack: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [64, 64, 1] - [64, 64, 16] std: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] sub: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] sub_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] - [64, 64, 65536] sum: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] sum_dim: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] sum_dim_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] sum_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] svd: shape_desc: (*B), M, N shapes: - [4096, 2, 2] - [4096, 16, 2] - [4096, 2, 16] - [4096, 8, 8] - [256, 16, 8] - [256, 8, 16] - [64, 32] - [32, 64] - [16, 16, 16] - [17, 17] - [256, 256] swiglu: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [1024, 8192] - [1024, 131072] - [64, 64, 2] - [64, 64, 32] - [64, 64, 512] - [64, 64, 8192] t_copy: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] t_copy_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] tan: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] tan_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] tanh: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] tanh_: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] tanh_backward: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] tensor_split: shape_desc: M, N shapes: - [64] - [256] - [1024] - [64, 64] - [128, 128] - [256, 256] - [512, 512] - [8, 16, 32] - [16, 32, 64] - [32, 64, 128] - [4, 8, 16, 32] - [8, 16, 32, 64] threshold: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] threshold_backward: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] tile: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [64, 512, 512] - [16, 256, 256] - [512, 512, 512] - [64, 64, 64, 64] top_k_per_row_decode: shape_desc: vocab_size, top_k shapes: - [129280, 1024] - [32768, 512] - [16384, 256] - [8192, 128] - [4096, 64] top_k_per_row_prefill: shape_desc: num_rows, vocab_size, top_k shapes: - [1, 129280, 1024] - [32, 129280, 1024] - [64, 129280, 1024] - [2048, 129280, 1024] topk: shape_desc: M, N shapes: - [64, 64] - [4096, 4096] - [10000, 256] - [10000, 65536] - [4, 128] - [8, 256] - [64, 128, 8] - [64, 1024, 32] - [64, 8192, 128] - [128, 32768, 256] - - [4, 128, 64] - 5 - - [4, 128, 64] - 64 - - [8, 512, 32] - 32 - - [16, 1024, 256] - 256 topk_softmax: shape_desc: M, N shapes: - [256, 128, 16] - [1024, 256, 32] - [4096, 64, 8] - [8192, 128, 8] - [16384, 256, 8] topk_softplus_sqrt: shape_desc: num_tokens, num_experts, topk shapes: - [1, 256, 6] - [10, 256, 6] - [16, 256, 6] - [128, 256, 6] - [512, 256, 6] - [1024, 256, 6] - [2048, 256, 6] - [4096, 256, 6] tril: shape_desc: (B), M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 16, 16] - [512, 32, 32] - [128, 64, 64] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] tril_: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] tril_extreme_diagonal: shape_desc: M, N shapes: - [4096, 4096] tril_out: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] tril_out_sliced: shape_desc: (B), M, N shapes: - [1024, 1024] - [16, 128, 128] - [512, 32, 32] tril_out_transposed: shape_desc: (B), M, N shapes: - [1024, 1024] - [16, 128, 128] - [512, 32, 32] triu: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] triu_: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] trunc_divide: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] trunc_divide_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] unfold_backward: shape_desc: M, N shapes: - - [32, 64] - 1 - 16 - 16 - - [16, 33] - 0 - 5 - 2 - - [4, 8, 12] - -1 - 6 - 4 - - [7, 13] - 1 - 13 - 3 - - [6, 20] - 1 - 7 - 4 - - [2, 3, 17] - -1 - 9 - 1 - - [2, 17] - 1 - 4 - 6 uniform_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] unique2: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] unique_consecutive: shape_desc: M, N shapes: - [64, 64] - [256, 256] - [1024, 1024] - [4096, 4096] - [1024, 65536] - [10000, 1] - [10000, 256] - [10000, 65536] unpack_seq_triton: shape_desc: N, D, B, lengths shapes: - - 512 - 64 - 5 - [64, 128, 64, 128, 128] - - 4096 - 128 - 4 - [1024, 1024, 1024, 1024] - - 8192 - 256 - 5 - [1024, 2048, 1024, 2048, 2048] - - 2048 - 512 - 4 - [512, 512, 512, 512] - - 16384 - 64 - 8 - [2048, 2048, 2048, 2048, 2048, 2048, 2048, 2048] - - 1024 - 1024 - 4 - [256, 256, 256, 256] upsample_bicubic2d_aa: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] upsample_bicubic2d_aa_backward: shape_desc: N, C, input_h, input_w, output_h, output_w, align_corners shapes: - [4, 16, 4, 4, 1, 1, false] - [4, 16, 4, 4, 16, 16, false] - [4, 16, 16, 16, 4, 4, false] - [4, 16, 16, 32, 64, 128, false] - [1, 1, 64, 64, 16, 16, false] - [1, 1, 64, 64, 32, 32, false] - [1, 1, 64, 64, 128, 128, false] - [4, 3, 256, 256, 128, 128, false] - [4, 3, 128, 128, 256, 256, false] - [4, 64, 64, 64, 32, 32, false] - [1, 64, 512, 512, 128, 128, false] - [1, 64, 512, 512, 1024, 1024, false] - [512, 1024, 32, 32, 8, 8, false] - [256, 512, 64, 64, 16, 16, false] - [256, 512, 64, 64, 32, 32, false] - [256, 512, 64, 64, 128, 128, false] upsample_linear1d: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] upsample_nearest1d: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] upsample_nearest2d: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] upsample_nearest3d: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] upsample_nearest_exact1d: shape_desc: M, N shapes: - [2, 3, 16] - [4, 8, 64] - [8, 16, 256] - [16, 32, 512] upsample_trilinear3d: shape_desc: N, C, H, W shapes: - [1, 3, 512, 512] - [8, 16, 128, 128] - [2, 3, 1024, 1024] - [16, 16, 512, 512] - [16, 16, 1024, 1024] var: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] var_correction: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] var_mean: shape_desc: M, N shapes: - [1048576] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1049600] - [1073741824] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [1024, 1048576] - [64, 1, 64] - [64, 16, 64] - [64, 256, 64] - [64, 4096, 64] vdot: shape_desc: M shapes: - [64] - [1024] - [2048] - [4096] - [65536] vector_norm: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] view_copy: shape_desc: (B), M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 1] - [1024, 16] - [1024, 256] - [1024, 4096] - [1024, 65536] - [64, 64, 1] - [64, 64, 16] - [64, 64, 256] - [64, 64, 4096] vstack: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [1024, 2] - [1024, 32] - [1024, 512] - [64, 64, 1] - [64, 64, 16] w8a8_block_fp8_matmul: shape_desc: M, N, K shapes: - [64, 128, 128] - [128, 256, 512] - [1, 4096, 7168] - [16, 4096, 7168] - [64, 4096, 7168] - [83, 7748, 3884] - [84, 7168, 3884] w8a8_block_fp8_matmul_deepgemm: shape_desc: M, N, K shapes: - [64, 128, 128] - [128, 256, 512] - [1, 4096, 7168] - [16, 4096, 7168] - [64, 4096, 7168] weight_norm: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] weight_norm_interface: shape_desc: M, N shapes: - [64, 64] - [1024, 1024] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] where_self: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] where_self_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] zero: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] zero_: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] zero_out: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] zeros: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100] zeros_like: shape_desc: M, N shapes: - [1073741824] - [64, 64] - [4096, 4096] - [64, 512, 512] - [1024, 1024, 1024] - [268435456] - [10000, 1] - [10000, 256] - [10000, 65536] - [100, 1, 100] - [100, 256, 100] - [100, 65536, 100]