From 0f9025cceb12da5a62fd17eea5a2f2bd3ec1914c Mon Sep 17 00:00:00 2001 From: LI SHENGYONG <49200266+shenchuxiaofugui@users.noreply.github.com> Date: Fri, 21 Nov 2025 18:18:15 +0800 Subject: [PATCH] [EPLB] Eplb Verify Fix (#4334) ### What this PR does / why we need it? Eplb Verify Fix --------- Signed-off-by: shenchuxiaofugui <1311027364@qq.com> Signed-off-by: LI SHENGYONG <49200266+shenchuxiaofugui@users.noreply.github.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> --- vllm_ascend/ops/common_fused_moe.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/vllm_ascend/ops/common_fused_moe.py b/vllm_ascend/ops/common_fused_moe.py index 412569d..3145b92 100644 --- a/vllm_ascend/ops/common_fused_moe.py +++ b/vllm_ascend/ops/common_fused_moe.py @@ -250,7 +250,8 @@ class AscendFusedMoE(FusedMoE): dtype=torch.int64).npu() eplb_enable = self.dynamic_eplb or (self.expert_map_path is not None) - if eplb_enable and (not isinstance(self.quant_method, + if eplb_enable and (not hasattr(self.quant_method, "quant_method") or + not isinstance(self.quant_method.quant_method, AscendW8A8DynamicFusedMoEMethod)): raise ValueError("Eplb supports only w8a8_dynamic quantization.")