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", )