# 由 gen_inventory.py 从 shapes_single.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:
  - [4096, 4096]
abs_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
absolute:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
acos:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
act_quant_triton:
  shape_desc: M, N
  shapes:
  - [1, 128]
add_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
add_rms_norm:
  shape_desc: M, N
  shapes:
  - [64, 64]
addcdiv:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
addcdiv_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
addcmul:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
addcmul_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
addmm:
  shape_desc: B, M, N, K
  shapes:
  - [16, 2048, 2048, 2048]
addmm_dtype:
  shape_desc: B, M, N, K
  shapes:
  - [16, 2048, 2048, 2048]
addmm_dtype_out:
  shape_desc: B, M, N, K
  shapes:
  - [16, 2048, 2048, 2048]
addmm_out:
  shape_desc: B, M, N, K
  shapes:
  - [16, 2048, 2048, 2048]
addmv:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
addr:
  shape_desc: B, M, N, K
  shapes:
  - [16, 1024, 1024, 1024]
alias_copy:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
alias_copy_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
all:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
all_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
allclose:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
amax:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
aminmax:
  shape_desc: M, N
  shapes:
  - [1048576]
angle:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
any:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
any_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
any_dims:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
apply_repetition_penalties:
  shape_desc: M, N
  shapes:
  - [64, 32000]
apply_rotary_pos_emb:
  shape_desc: M, N
  shapes:
  - [512]
arange:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
arange_start:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
arange_start_step:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
arcsinh:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
arcsinh_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
arcsinh_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
arctanh_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
argmax:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
argmin:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
argsort:
  shape_desc: M, N
  shapes:
  - [64, 64]
as_strided_copy:
  shape_desc: input shape, size, stride, storage_offset
  shapes:
  - - [64, 64]
    - [64, 64]
    - [64, 1]
    - 0
as_strided_copy_out:
  shape_desc: input shape, size, stride, storage_offset
  shapes:
  - - [64, 64]
    - [64, 64]
    - [64, 1]
    - 0
asinh:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
asinh_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
assert_async:
  shape_desc: M, N
  shapes:
  - []
atan:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
atan2:
  shape_desc: M, N
  shapes:
  - [64, 64]
atan2_out:
  shape_desc: M, N
  shapes:
  - [64, 64]
atan_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
atanh:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
avg_pool2d:
  shape_desc: N, C, H, W
  shapes:
  - [32, 128, 28, 28]
avg_pool2d_backward:
  shape_desc: N, C, H, W
  shapes:
  - [32, 128, 28, 28]
avg_pool3d:
  shape_desc: N, C, D, H, W
  shapes:
  - [8, 64, 8, 28, 28]
baddbmm:
  shape_desc: B, M, N, K
  shapes:
  - [16, 1024, 1024, 1024]
batch_norm:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
batch_norm_backward:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
bernoulli_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bincount:
  shape_desc: M, N
  shapes:
  - [10000, 1]
bincount_weighted:
  shape_desc: M, N
  shapes:
  - [10000, 1]
bitwise_and_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_and_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_and_scalar_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_and_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_and_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_left_shift:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_not:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
bitwise_not_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
bitwise_or_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_or_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_or_scalar_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_or_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_or_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bitwise_right_shift:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
bmm:
  shape_desc: B, M, N, K
  shapes:
  - [16, 1024, 1024, 1024]
bmm_out:
  shape_desc: B, M, N, K
  shapes:
  - [16, 1024, 1024, 1024]
cat_out:
  shape_desc: M, N
  shapes:
  - [64, 64]
cauchy:
  shape_desc: M, N
  shapes:
  - [64, 64]
cauchy_:
  shape_desc: M, N
  shapes:
  - [64, 64]
cdist_backward:
  shape_desc: batch, n1, dim
  shapes:
  - [2, 16, 32]
  - [4, 32, 64]
  - [8, 64, 128]
ceil:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
ceil_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
ceil_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
celu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
celu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 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:
  - [4096, 4096]
clamp_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clamp_max:
  shape_desc: M, N
  shapes:
  - [64, 64]
clamp_max_:
  shape_desc: M, N
  shapes:
  - [64, 64]
clamp_min:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clamp_min_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clamp_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clamp_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clip:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
clip_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
col2im:
  shape_desc: M, N
  shapes:
  - - 4
    - 32
    - [3, 3]
    - [32, 32]
    - [1, 1]
    - [1, 1]
    - [1, 1]
combine_topk_swa_indices:
  shape_desc: M, N
  shapes:
  - - [3, 2]
    - [6, 4]
    - [4, 3]
    - 4
    - 4
    - 2
    - 20
    - 8
compute_global_topk_indices_and_lens:
  shape_desc: M, N
  shapes:
  - [5, 4, 2, 4, 64]
concat_and_cache_mla:
  shape_desc: M, N
  shapes:
  - [16, 8, 84, 32, 4]
concatenate:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
conj_physical:
  shape_desc: M, N
  shapes:
  - [2048, 2048]
constant_pad_nd:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
contiguous:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
conv1d:
  shape_desc: N, C, L, Co, K, stride, padding, groups
  shapes:
  - [64, 32, 512, 32, 5, 2, 2, 1]
conv1d_padding:
  shape_desc: batch, input_c, input_l, out_c, kernel, stride, padding, groups
  shapes:
  - [64, 48, 1024, 128, 5, 2, 2, 1]
conv2d:
  shape_desc: N, C_in, H, W, C_out, K_h, K_w, stride, padding, groups
  shapes:
  - [104, 16, 32, 32, 32, 4, 4, 1, 0, 1]
conv2d_padding:
  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, same, 1]
conv3d:
  shape_desc: N, C_in, D, H, W, C_out, K_d, K_h, K_w, stride, padding, groups
  shapes:
  - [16, 32, 24, 24, 24, 24, 3, 3, 3, 1, 1, 2]
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:
  - [32, 8, 8, 8, 8, 32, 3, 3, 3, 1, valid, 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]
conv_transpose1d:
  shape_desc: batch, input_c, input_l, out_c, kernel, stride, padding, groups
  shapes:
  - [64, 48, 256, 128, 5, 2, 2, 1]
conv_transpose2d:
  shape_desc: N, C_in, H, W, C_out, K_h, K_w, stride, padding, groups
  shapes:
  - [16, 32, 32, 32, 64, 3, 3, 2, 1, 1]
copy:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
copy_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
copysign:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
copysign_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
cos:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
cos_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
cosh:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
cosh_:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
cosh_out:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
count_nonzero:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
cp_gather_indexer_k_quant_cache:
  shape_desc: batch_size, seq_len, block_size, head_dim, quant_block_size
  shapes:
  - [32, 1024, 16, 512, 128]
cross_entropy_loss:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
ctc_loss:
  shape_desc: T, N, C, S
  shapes:
  - [256, 16, 64, 48]
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:
  - [16, 32, 12, 12, 24, 3, 3, 2, 1, 1]
cummax:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
cummin:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
cumprod:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
cumprod_:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
cumsum:
  shape_desc: M, N
  shapes:
  - [64, 64]
cutlass_scaled_mm:
  shape_desc: M, N, K
  shapes:
  - [16, 24576, 4096]
dequantize_and_gather_k_cache:
  shape_desc: M, N
  shapes:
  - [1, 512, 128, 512, 448, 64]
dgeglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
diag:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
diag_embed:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
diagonal_backward:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
diff:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
digamma_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
div_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
div_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dot:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dreglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
dropout:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
dropout_backward:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dswiglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
dunder_ior_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dunder_ior_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dunder_or_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
dunder_or_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
einsum:
  shape_desc: B, M, N, K
  shapes:
  - [1, 1024, 1024, 1024]
elu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
elu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
elu_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
embedding:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
embedding_backward:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
embedding_dense_backward:
  shape_desc: M, N
  shapes:
  - [8, 4096, 256, 32768]
eq:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
eq_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
erf:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
erf_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exp:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exp2:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exp2_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exp_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exp_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
expm1:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
expm1_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
expm1_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
exponential_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
eye:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
eye_m:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
feature_dropout:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
feature_dropout_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fft:
  shape_desc: M, N
  shapes:
  - [4096, 512]
fill_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fill_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fill_scalar_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fill_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fill_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fill_tensor_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
flash_mla:
  shape_desc: M, N
  shapes:
  - [1024]
flash_mla_sparse_fwd:
  shape_desc: s_q, s_kv, topk, h_q, d_qk
  shapes:
  - [4096, 8192, 2048, 128, 576]
flip:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
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:
  - [64, 64]
floor_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
floor_divide_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
floor_divide_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
floor_out:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
fmin:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fmin_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fmod_:
  shape_desc: M, N
  shapes:
  - [64, 64]
fmod_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fmod_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fmod_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fmod_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fp8_einsum:
  shape_desc: M, N
  shapes:
  - [128, 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]
full:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
full_like:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
functional_sym_constrain_range_for_size:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fused_add_rms_norm:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
fused_deepseek_v4_qnorm_rope_kv_rope_quant_insert:
  shape_desc: num_tokens, num_heads, num_tokens_insert, block_size, max_pos, eps
  shapes:
  - [2048, 128, 2048, 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]
fused_inv_rope_fp8_quant:
  shape_desc: num_tokens, num_heads, n_groups, tma_aligned_scales
  shapes:
  - [1024, 128, 8, false]
fused_marlin_moe:
  shape_desc: M, N
  shapes:
  - [1, 8, 4096, 14336, 2]
fused_marlin_moe_int8:
  shape_desc: M, N
  shapes:
  - [1, 8, 4096, 14336, 2]
fused_moe:
  shape_desc: M, N
  shapes:
  - [1, 8, 4096, 14336, 2]
fused_moe_int8_w8a16_gems_vs_bf16_deq:
  shape_desc: M, N
  shapes:
  - [1, 8, 4096, 14336, 2]
fused_q_kv_rmsnorm:
  shape_desc: M, N
  shapes:
  - [1, 1536, 512]
gather:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
gather_backward:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
gcd:
  shape_desc: (B), M, N
  shapes:
  - [64, 256, 256]
gcd_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
ge:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
ge_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
geglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
gelu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
gelu_and_mul:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
gelu_backward:
  shapes:
  - [1048576]
  - [64, 64]
  - [4096, 4096]
  - [64, 512, 512]
  - [256, 1024, 1024]
glu:
  shape_desc: M, N
  shapes:
  - [4, 8, 2048, 128]
glu_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
greater:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
greater_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
greater_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
greater_scalar_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
grid_sample:
  shape_desc: M, N
  shapes:
  - [4, 64, 64, 64]
group_norm:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
grouped_mm:
  shape_desc: Groups, N, K
  shapes:
  - [16, 512, 2048]
  - [16, 2560, 2048]
  - [64, 2048, 128]
grouped_topk:
  shape_desc: M, N
  shapes:
  - [1024, 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:
  - [4096, 4096]
gt_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
hadamard_transform:
  shape_desc: batch, dim
  shapes:
  - [64, 64]
hadamard_transform_mn:
  shape_desc: batch, dim
  shapes:
  - [1024, 40960]
hardsigmoid:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
hardswish_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
hc_head_fused_kernel:
  shape_desc: N, hidden_size
  shapes:
  - [4096, 4096, 4]
hc_split_sinkhorn_forward:
  shape_desc: batch, seqlen
  shapes:
  - [256, 256, 4]
histc:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
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:
  - [4096, 4096]
hypot_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
i0:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
i0_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
i0_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
index:
  shape_desc: M, N
  shapes:
  - - [268435456]
    - - [65536]
index_add:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
index_add_:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
index_copy:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
index_copy_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
index_put:
  shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate
  shapes:
  - - [268435456]
    - - [65536]
    - [65536]
    - false
index_put_:
  shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate
  shapes:
  - - [268435456]
    - - [65536]
    - [65536]
    - false
index_put_impl:
  shape_desc: input_shape, [index_tensor_shapes], values_shape, accumulate
  shapes:
  - - [268435456]
    - - [65536]
    - [65536]
    - false
index_select:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
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:
  - [2048, 256, 16, 512, 128]
inplace_fused_experts:
  shape_desc: M, N
  shapes:
  - [16, 8, 4096, 14336, 2]
instance_norm:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
is_all_true:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
isclose:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
isfinite:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
isin:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
isin_scalar_tensor:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
isin_tensor_scalar:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
isinf:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
isnan:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
isneginf:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
kron:
  shape_desc: M, N
  shapes:
  - [256, 256]
layer_norm:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
layer_norm_backward:
  shape_desc: N, C, *
  shapes:
  - [20, 6, 65536]
le:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
le_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
leaky_relu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
leaky_relu_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
lerp_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lerp_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lerp_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lerp_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lift_fresh_copy:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
linspace:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
log:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
log10:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
log10_:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
log10_out:
  shape_desc: (B), M, N
  shapes:
  - [1024, 65536]
log1p:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
log1p_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
log_sigmoid:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
log_softmax:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
log_softmax_backward_data:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
log_softmax_backward_data_out:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
log_softmax_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logaddexp:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logaddexp_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logical_and:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logical_and_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logical_not:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
logical_or:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logical_or_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logical_xor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logit:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
logit_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
logspace:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
logsumexp:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lt:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
lt_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
margin_ranking_loss:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_fill:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_fill_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_fill_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_fill_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_scatter:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_scatter_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
masked_select:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
max:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
max_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
max_pool2d_backward:
  shape_desc: N, C, H, W
  shapes:
  - [32, 128, 28, 28]
max_pool2d_with_indices:
  shape_desc: N, C, H, W
  shapes:
  - [32, 128, 28, 28]
max_pool3d:
  shape_desc: N, C, D, H, W
  shapes:
  - [4, 3, 16, 56, 56]
max_pool3d_backward:
  shape_desc: N, C, D, H, W
  shapes:
  - [4, 3, 16, 56, 56]
maximum:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mean:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mean_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
median:
  shape_desc: input shape
  shapes:
  - [4096]
median_dim:
  shape_desc: input shape or [input shape, dim, keepdim]
  shapes:
  - - [32, 384, 128]
    - 1
    - false
mhc_bwd:
  shape_desc: seqlen, n_stream
  shapes:
  - [65536, 4]
mhc_post:
  shape_desc: N, H
  shapes:
  - [4096, 7168]
mhc_pre:
  shape_desc: N, hidden_size
  shapes:
  - [8192, 2560]
min:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
min_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
minimum:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mm:
  shape_desc: B, M, N, K
  shapes:
  - [2, 384, 384, 384]
mm_out:
  shape_desc: B, M, N, K
  shapes:
  - [2, 384, 384, 384]
mm_self_transpose:
  shape_desc: M, K
  shapes:
  - [1024, 1024]
moe_align_block_size_triton:
  shape_desc: M, N
  shapes:
  - [512, 64, 16384, 10]
moe_sum:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mse_loss:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mul:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
mul_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
multinomial:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
mv:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
nan_to_num:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
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:
  - [4096, 4096]
ne_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
neg:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
neg_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
new_full:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
nll_loss2d_backward:
  shape_desc: M, N
  shapes:
  - [256, 256, 4, 8]
nll_loss2d_forward:
  shape_desc: M, N
  shapes:
  - [1024, 1024, 4, 8]
nll_loss_backward:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
nll_loss_forward:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
nll_loss_nd_backward:
  shape_desc: N, C, d1, d2, ...
  shapes:
  - [64, 64]
nll_loss_nd_forward:
  shape_desc: N, C, d1, d2, ...
  shapes:
  - [32, 128, 512]
nonzero:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
nonzero_numpy:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
normal_float_float_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
normal_float_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
normal_tensor_float:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
normal_tensor_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
one_hot:
  shape_desc: M, N
  shapes:
  - [64, 64]
ones:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
ones_like:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
outer:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
pack_seq_triton:
  shape_desc: N, D, B, lengths
  shapes:
  - - 512
    - 64
    - 5
    - [64, 128, 64, 128, 128]
pad:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
per_token_group_quant_fp8:
  shape_desc: M, N
  shapes:
  - [7, 4096, 256]
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:
  - - [4, 16, 64, 48]
    - 4
poisson:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
polar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
pow_tensor_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
pow_tensor_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
prelu:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
prod:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
quantile:
  shape_desc: M, N
  shapes:
  - [1048576]
rad2deg:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
rad2deg_:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
rand:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
rand_like:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
randint:
  shape_desc: M, N
  shapes:
  - [64, 64]
randint_like:
  shape_desc: M, N
  shapes:
  - [64, 64]
randn:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
randn_like:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
randperm:
  shape_desc: M
  shapes:
  - [65536]
reciprocal:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
reciprocal_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
reflection_pad1d:
  shape_desc: M, N
  shapes:
  - - [8, 16, 256]
    - [8, 8]
reflection_pad1d_backward:
  shape_desc: M, N
  shapes:
  - [2, 3]
reflection_pad1d_out:
  shape_desc: M, N
  shapes:
  - - [8, 16, 256]
    - [8, 8]
reflection_pad2d:
  shape_desc: M, N
  shapes:
  - - [16, 32, 64, 128]
    - [1, 1, 1, 1]
reflection_pad2d_out:
  shape_desc: M, N
  shapes:
  - - [16, 32, 64, 128]
    - [1, 1, 1, 1]
reglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
relu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
relu6:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
relu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
remainder:
  shape_desc: M, N
  shapes:
  - [64, 64]
remainder_scalar_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
remainder_scalar_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
remainder_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
remainder_tensor_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
renorm:
  shape_desc: M, N
  shapes:
  - [4, 8]
repeat:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
repeat_interleave_self_int:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
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:
  - - [8, 32, 256]
    - [1, 2]
replication_pad3d:
  shape_desc: M, N
  shapes:
  - [2, 32, 16, 128, 128]
reshape_and_cache:
  shape_desc: M, N
  shapes:
  - [42, 8, 80, 16, 10000]
reshape_and_cache_flash:
  shape_desc: M, N
  shapes:
  - [42, 8, 80, 16, 10000]
resolve_conj:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
resolve_neg:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
rms_norm:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
roll:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
rot90:
  shape_desc: M, N
  shapes:
  - [64, 64]
round:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
round_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
round_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
router_gemm:
  shape_desc: M, N, K
  shapes:
  - [1024, 8, 4096]
rrelu_with_noise_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
rsqrt:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
rsqrt_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
rsub_scalar:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
rsub_tensor:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
rwkv_ka_fusion:
  shape_desc: M, N
  shapes:
  - [32768]
rwkv_mm_sparsity:
  shape_desc: M, N
  shapes:
  - [1]
safe_softmax:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
scaled_dot_product_attention:
  shape_desc: M, N
  shapes:
  - [4, 32, 1024, 64]
scaled_mm:
  shape_desc: M, N, K
  shapes:
  - [16, 16, 16]
scaled_mm_out:
  shape_desc: M, N, K
  shapes:
  - [16, 16, 16]
scaled_softmax_backward:
  shape_desc: batch, heads, query_len, key_len
  shapes:
  - [2, 8, 128, 128]
scaled_softmax_forward:
  shape_desc: batch, heads, query_len, key_len
  shapes:
  - [2, 8, 128, 128]
scatter_add_:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
scatter_reduce.two:
  shape_desc: M, N
  shapes:
  - [64, 64]
scatter_src:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
scatter_src_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
searchsorted:
  shape_desc: sorted_sequence shape, values shape, sorter, right, out_int32
  shapes:
  - - [1024]
    - [4096]
    - false
    - false
    - false
searchsorted_out:
  shape_desc: sorted_sequence shape, values shape, sorter, right, out_int32
  shapes:
  - - [1024]
    - [4096]
    - false
    - false
    - false
searchsorted_scalar:
  shape_desc: sorted_sequence shape, right, out_int32
  shapes:
  - - [1024]
    - false
    - false
searchsorted_scalar_out:
  shape_desc: sorted_sequence shape, right, out_int32
  shapes:
  - - [1024]
    - false
    - false
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]
select_scatter:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
selu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
selu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sgn_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sigmoid:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sigmoid_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sigmoid_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
signbit:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
silu:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
silu_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
silu_and_mul:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
silu_and_mul_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
silu_and_mul_with_clamp:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
silu_and_mul_with_clamp_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
silu_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sin:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sin_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
single_dim_shapes:
  shape_desc: M
  shapes:
  - [64]
  - [1024]
  - [2048]
  - [4096]
  - [65536]
sinh_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
skip_layer_norm:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
slice_backward:
  shape_desc: M, N
  shapes:
  - [128, 256]
slice_scatter:
  shape_desc: M, N
  shapes:
  - [1024, 65536]
smooth_l1_loss:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
smooth_l1_loss_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
soft_margin_loss:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
softmax:
  shape_desc: M, N
  shapes:
  - [1048576]
softmax_backward:
  shapes:
  - [1048576]
  - [64, 64]
  - [4096, 4096]
  - [64, 512, 512]
  - [256, 1024, 1024]
softmax_backward_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
softmax_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
softplus:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
softshrink:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
softshrink_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sort:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
sort_stable:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
sparse_attention:
  shape_desc: B, M, KV_LEN, TOPK, H, D
  shapes:
  - [16, 1, 136, 136, 8, 512]
special_i0e:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
special_i0e_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
special_i1:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
special_i1_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
split_with_sizes_copy:
  shape_desc: M, N
  shapes:
  - [10, 4]
sqrt:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
sqrt_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
square:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
square_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
square_out:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
stack:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
std:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sub:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sub_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sum:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sum_dim:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sum_dim_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
sum_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
svd:
  shape_desc: (*B), M, N
  shapes:
  - [4096, 8, 8]
swiglu:
  shape_desc: M, N
  shapes:
  - [64, 64]
t_copy:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
t_copy_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
tan:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tan_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tanh:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tanh_:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tanh_backward:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tensor_split:
  shape_desc: M, N
  shapes:
  - [64, 64]
threshold:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
threshold_backward:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
tile:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
top_k_per_row_decode:
  shape_desc: vocab_size, top_k
  shapes:
  - [32768, 512]
top_k_per_row_prefill:
  shape_desc: num_rows, vocab_size, top_k
  shapes:
  - [1, 129280, 1024]
topk:
  shape_desc: M, N
  shapes:
  - [128, 32768, 256]
topk_softmax:
  shape_desc: M, N
  shapes:
  - [8192, 128, 8]
topk_softplus_sqrt:
  shape_desc: num_tokens, num_experts, topk
  shapes:
  - [4096, 256, 6]
tril:
  shape_desc: (B), M, N
  shapes:
  - [4096, 4096]
tril_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
tril_extreme_diagonal:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
tril_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
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:
  - [4096, 4096]
triu_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
trunc_divide:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
trunc_divide_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
unfold_backward:
  shape_desc: M, N
  shapes:
  - - [32, 64]
    - 1
    - 16
    - 16
uniform_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
unique2:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
unique_consecutive:
  shape_desc: M, N
  shapes:
  - [1024, 1024]
unpack_seq_triton:
  shape_desc: N, D, B, lengths
  shapes:
  - - 512
    - 64
    - 5
    - [64, 128, 64, 128, 128]
upsample_bicubic2d_aa:
  shape_desc: N, C, H, W
  shapes:
  - [8, 16, 128, 128]
upsample_bicubic2d_aa_backward:
  shape_desc: N, C, input_h, input_w, output_h, output_w, align_corners
  shapes:
  - [4, 64, 64, 64, 32, 32, false]
upsample_linear1d:
  shape_desc: N, C, H, W
  shapes:
  - [8, 16, 128, 128]
upsample_nearest1d:
  shape_desc: N, C, H, W
  shapes:
  - [16, 16, 512, 512]
upsample_nearest2d:
  shape_desc: N, C, H, W
  shapes:
  - [16, 16, 512, 512]
upsample_nearest3d:
  shape_desc: N, C, H, W
  shapes:
  - [16, 16, 512, 512]
upsample_nearest_exact1d:
  shape_desc: M, N
  shapes:
  - [16, 32, 512]
upsample_trilinear3d:
  shape_desc: N, C, H, W
  shapes:
  - [1, 3, 512, 512]
var:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
var_correction:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
var_mean:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
vdot:
  shape_desc: M
  shapes:
  - [65536]
vector_norm:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
view_copy:
  shape_desc: (B), M, N
  shapes:
  - [64, 64]
vstack:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
w8a8_block_fp8_matmul:
  shape_desc: M, N, K
  shapes:
  - [64, 4096, 7168]
w8a8_block_fp8_matmul_deepgemm:
  shape_desc: M, N, K
  shapes:
  - [64, 4096, 7168]
weight_norm:
  shape_desc: M, N
  shapes:
  - [64, 512, 512]
weight_norm_interface:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
where_self:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
where_self_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
zero:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
zero_:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
zero_out:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
zeros:
  shape_desc: M, N
  shapes:
  - [4096, 4096]
zeros_like:
  shape_desc: M, N
  shapes:
  - [4096, 4096]