zhoulin
00902e6c67
Plain autotune is the common case (fast, same-config A/B); FlagTune's exhaustive first-run search is now opt-in via USE_FLAGTUNE=1. ab_fold_test.sh automates the FLAGGEMS_MXFP4_FOLDSCALE=0/1 record-replay comparison over the four DeepSeek-V4-Flash trace shape sets, which are now tracked under runs/shape/.
58 lines
2.6 KiB
YAML
58 lines
2.6 KiB
YAML
fused_marlin_moe_mxfp4:
|
||
# 来源: DeepSeek-V4-Flash-p32768d1024.txt（53 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
|
||
- [16384, 256, 4096, 256, 6] # count: 946
|
||
shape_desc: "num_tokens, num_experts, hidden_size, intermediate_size, topk"
|