iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Bugfix] Handle DeepseekV4ForCausalLM in benchmark_moe get_model_params (#52044)

Browse Source 
Co-authored-by: Do_it_now_! <23432123@users.noreply.github.com>
This commit is contained in:
Do_it_now_!
2026-08-18 04:46:08 +00:00
committed by GitHub
co-authored by Do_it_now_!
parent e0e5a7fb28
commit 101c4477dd
1 changed files with 1 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
benchmarks/kernels/benchmark_moe.py
+1
View File
@@ -766,6 +766,7 @@ def get_model_params(config):
"DeepseekV2ForCausalLM",
"DeepseekV3ForCausalLM",
"DeepseekV32ForCausalLM",
"DeepseekV4ForCausalLM",
"GlmMoeDsaForCausalLM",
"Glm4MoeForCausalLM",
"Glm4MoeLiteForCausalLM",