biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Kernel] Delegate construction of FusedMoEQuantConfig to FusedMoEMethodBase subclasses (#22537)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
This commit is contained in:
bnellnm
2025-09-17 19:43:31 -04:00
committed by GitHub
parent e6585ddb45
commit 5963b98b46
68 changed files with 2698 additions and 2526 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/models/qwen3_moe.py
View File

@@ -702,4 +702,4 @@ class Qwen3MoeForCausalLM(nn.Module, SupportsPP, SupportsLoRA,
return loader.load_weights(weights)
def get_expert_mapping(self) -> list[tuple[str, str, int, str]]:
return self.model.get_expert_mapping()
return self.model.get_expert_mapping()