fused_marlin_moe_mxfp4: # 来源: DeepSeek-V4-Flash-p1024d1024.txt(55 个去重 shape,按 num_tokens 升序;行尾注释为 trace 中的调用次数) shapes: - [1, 256, 4096, 256, 6] # count: 172 - [2, 256, 4096, 256, 6] # count: 172 - [4, 256, 4096, 256, 6] # count: 172 - [8, 256, 4096, 256, 6] # count: 172 - [16, 256, 4096, 256, 6] # count: 172 - [24, 256, 4096, 256, 6] # count: 172 - [32, 256, 4096, 256, 6] # count: 172 - [40, 256, 4096, 256, 6] # count: 172 - [48, 256, 4096, 256, 6] # count: 172 - [56, 256, 4096, 256, 6] # count: 172 - [64, 256, 4096, 256, 6] # count: 172 - [72, 256, 4096, 256, 6] # count: 172 - [80, 256, 4096, 256, 6] # count: 172 - [88, 256, 4096, 256, 6] # count: 172 - [96, 256, 4096, 256, 6] # count: 172 - [104, 256, 4096, 256, 6] # count: 172 - [112, 256, 4096, 256, 6] # count: 172 - [120, 256, 4096, 256, 6] # count: 172 - [128, 256, 4096, 256, 6] # count: 172 - [136, 256, 4096, 256, 6] # count: 172 - [144, 256, 4096, 256, 6] # count: 172 - [152, 256, 4096, 256, 6] # count: 172 - [160, 256, 4096, 256, 6] # count: 172 - [168, 256, 4096, 256, 6] # count: 172 - [176, 256, 4096, 256, 6] # count: 172 - [184, 256, 4096, 256, 6] # count: 172 - [192, 256, 4096, 256, 6] # count: 172 - [200, 256, 4096, 256, 6] # count: 172 - [208, 256, 4096, 256, 6] # count: 172 - [216, 256, 4096, 256, 6] # count: 172 - [224, 256, 4096, 256, 6] # count: 172 - [232, 256, 4096, 256, 6] # count: 172 - [240, 256, 4096, 256, 6] # count: 172 - [248, 256, 4096, 256, 6] # count: 172 - [256, 256, 4096, 256, 6] # count: 172 - [272, 256, 4096, 256, 6] # count: 172 - [288, 256, 4096, 256, 6] # count: 172 - [304, 256, 4096, 256, 6] # count: 172 - [320, 256, 4096, 256, 6] # count: 172 - [336, 256, 4096, 256, 6] # count: 172 - [352, 256, 4096, 256, 6] # count: 172 - [368, 256, 4096, 256, 6] # count: 172 - [384, 256, 4096, 256, 6] # count: 172 - [400, 256, 4096, 256, 6] # count: 172 - [416, 256, 4096, 256, 6] # count: 172 - [432, 256, 4096, 256, 6] # count: 172 - [448, 256, 4096, 256, 6] # count: 172 - [464, 256, 4096, 256, 6] # count: 172 - [480, 256, 4096, 256, 6] # count: 172 - [496, 256, 4096, 256, 6] # count: 344 - [512, 256, 4096, 256, 6] # count: 344 - [1028, 256, 4096, 256, 6] # count: 215 - [2048, 256, 4096, 256, 6] # count: 43 - [3805, 256, 4096, 256, 6] # count: 215 - [16384, 256, 4096, 256, 6] # count: 1376 shape_desc: "num_tokens, num_experts, hidden_size, intermediate_size, topk"