Move trace shape sets to top-level shape/ and frame ab_fold_test.sh as A/B reference example

This commit is contained in:
2026-07-20 16:53:14 +00:00
parent 00902e6c67
commit c8a42b66ee
11 changed files with 9 additions and 8 deletions
+59
View File
@@ -0,0 +1,59 @@
fused_marlin_moe_mxfp4:
# 来源: DeepSeek-V4-Flash-p4096d1024.txt55 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
- [2048, 256, 4096, 256, 6] # count: 43
- [4100, 256, 4096, 256, 6] # count: 215
- [13021, 256, 4096, 256, 6] # count: 215
- [16384, 256, 4096, 256, 6] # count: 3311
shape_desc: "num_tokens, num_experts, hidden_size, intermediate_size, topk"