From 33a0d43c7119269aa300d4341871dd46d52575d0 Mon Sep 17 00:00:00 2001 From: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com> Date: Tue, 24 Feb 2026 07:42:24 +0400 Subject: [PATCH] [BUGFIX][Qwen3.5] Hardcode `mlp.gate` as not quantizable (#35156) Signed-off-by: Vadim Gimpelson --- vllm/model_executor/models/qwen3_next.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/vllm/model_executor/models/qwen3_next.py b/vllm/model_executor/models/qwen3_next.py index 16116c67a..777d1d7bf 100644 --- a/vllm/model_executor/models/qwen3_next.py +++ b/vllm/model_executor/models/qwen3_next.py @@ -252,7 +252,7 @@ class Qwen3NextSparseMoeBlock(nn.Module): config.hidden_size, config.num_experts, bias=False, - quant_config=quant_config, + quant_config=None, prefix=f"{prefix}.gate", )