Fix test and benchmark scripts (#2598)

2024-12-26 07:56:26 -08:00
parent a74d194146
commit dc3bee4815
9 changed files with 27 additions and 21 deletions
--- a/python/sglang/srt/layers/moe/fused_moe_triton/configs/README
+++ b/python/sglang/srt/layers/moe/fused_moe_triton/configs/README
@@ -8,3 +8,5 @@ the JSON file contains a mapping from M (batch size) to the chosen configuration
 The example configurations provided are for the Mixtral model for TP2 on H100
 and TP4 on A100. Mixtral has intermediate size N = 14336, i.e. for TP2 we have
 N = 7168 and for TP4 we have N = 3584.
+
+See `benchmark/kernels/fused_moe_triton/README.md` on how to generate these config files.