minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 10 Packages Projects Releases Wiki Activity

[Kernel] Add fused MoE Triton configs for Qwen3.8-Flash-Next FP8 on NVIDIA H200 NVL (TP2+EP2) (#38116)

Browse Source
This commit is contained in:
Chan ahn
2026-09-07 10:17:55 -07:00
committed by GitHub
parent c99d906eff
commit dcebe8c473
2 changed files with 147 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmark/kernels/fused_moe_triton/common_utils.py
+1
View File
@@ -84,6 +84,7 @@ def get_model_config(
"Qwen3VLMoeForConditionalGeneration",
"Qwen3_5MoeForCausalLM",
"Qwen3_5MoeForConditionalGeneration",
"Qwen4ExpForConditionalGeneration",
"InternS2PreviewForConditionalGeneration",
"MellumForCausalLM",
]: