From 3955bf29082f1e57e88ca58d2bfce63ba28301c6 Mon Sep 17 00:00:00 2001 From: LI SHENGYONG <49200266+shenchuxiaofugui@users.noreply.github.com> Date: Fri, 21 Nov 2025 18:17:46 +0800 Subject: [PATCH] [EPLB] Eplb Verify Fix (#4333) ### What this PR does / why we need it? Eplb Verify Fix ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? - vLLM version: v0.11.0 - vLLM main: https://github.com/vllm-project/vllm/commit/2918c1b49c88c29783c86f78d2c4221cb9622379 --------- 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/fused_moe/fused_moe.py | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/vllm_ascend/ops/fused_moe/fused_moe.py b/vllm_ascend/ops/fused_moe/fused_moe.py index 4eee35d0..a70a4cdf 100644 --- a/vllm_ascend/ops/fused_moe/fused_moe.py +++ b/vllm_ascend/ops/fused_moe/fused_moe.py @@ -257,7 +257,8 @@ 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.")