From 206b72c982db29eb10e475589cbf3fa8d6a37071 Mon Sep 17 00:00:00 2001 From: Minh Vu Date: Wed, 27 May 2026 19:51:56 +0200 Subject: [PATCH] [Quantization] Fix Humming RoutedExperts import (#43540) Signed-off-by: Minh Vu Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com> --- vllm/model_executor/layers/quantization/utils/humming_utils.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/layers/quantization/utils/humming_utils.py b/vllm/model_executor/layers/quantization/utils/humming_utils.py index 63735708b6..3c01977f3b 100644 --- a/vllm/model_executor/layers/quantization/utils/humming_utils.py +++ b/vllm/model_executor/layers/quantization/utils/humming_utils.py @@ -8,11 +8,11 @@ from humming.layer import HummingInputSchema, HummingMethod from humming.schema import BaseWeightSchema from vllm import envs +from vllm.model_executor.layers.fused_moe import RoutedExperts from vllm.model_executor.layers.fused_moe.config import ( FusedMoEQuantConfig, FusedMoEQuantDesc, ) -from vllm.model_executor.layers.fused_moe.routed_experts import RoutedExperts from vllm.model_executor.layers.linear import LinearBase from vllm.model_executor.layers.quantization.utils.quant_utils import GroupShape