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

[Bugfix] Fix misnamed parameter in compressed_tensors_moe.py (#35813)

Browse Source 
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
This commit is contained in:
bnellnm
2026-03-03 16:29:57 -05:00
committed by GitHub
parent e7213003cb
commit a9b8b13e5c
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py
View File

@@ -887,7 +887,7 @@ class CompressedTensorsW8A8Fp8MoEMethod(CompressedTensorsMoEMethod):
w13, w13,
w13_scale, w13_scale,
shard_size=layer.intermediate_size_per_partition, shard_size=layer.intermediate_size_per_partition,
num_experts=layer.num_local_experts, num_experts=layer.local_num_experts,
is_act_and_mul=self.moe.is_act_and_mul, is_act_and_mul=self.moe.is_act_and_mul,
) )