minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Kernel] Add H20 block-FP8 MoE configs for GLM-5.3-Flash EP4/EP8 (#38913)

Browse Source
This commit is contained in:
Hank Han
2026-09-15 23:42:18 -07:00
committed by GitHub
parent 6b33338242
commit a64be2e430
3 changed files with 293 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
@@ -107,6 +107,7 @@ def get_model_config(
"Glm4MoeForCausalLM",
"Glm4MoeLiteForCausalLM",
"GlmMoeDsaForCausalLM",
"Glm5NextForConditionalGeneration",
"KimiVLForConditionalGeneration",
"MistralLarge3ForCausalLM",
]: