From a9b8b13e5cdc52aa7f4472d4d21f178e3805bcdd Mon Sep 17 00:00:00 2001 From: bnellnm <49004751+bnellnm@users.noreply.github.com> Date: Tue, 3 Mar 2026 16:29:57 -0500 Subject: [PATCH] [Bugfix] Fix misnamed parameter in compressed_tensors_moe.py (#35813) Signed-off-by: Bill Nell Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com> --- .../quantization/compressed_tensors/compressed_tensors_moe.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py index 8b7fc57d04..f6c0009a5a 100644 --- a/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py +++ b/vllm/model_executor/layers/quantization/compressed_tensors/compressed_tensors_moe.py @@ -887,7 +887,7 @@ class CompressedTensorsW8A8Fp8MoEMethod(CompressedTensorsMoEMethod): w13, w13_scale, 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, )