EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

[EPLB] Eplb Verify Fix (#4334)

Browse Source 
### 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>
This commit is contained in:
LI SHENGYONG
2025-11-21 18:18:15 +08:00
committed by GitHub
parent 97ffb9120f
commit 0f9025cceb
1 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm_ascend/ops/common_fused_moe.py
View File

@@ -250,7 +250,8 @@ class AscendFusedMoE(FusedMoE):
dtype=torch.int64).npu() dtype=torch.int64).npu()
eplb_enable = self.dynamic_eplb or (self.expert_map_path is not None) 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)): AscendW8A8DynamicFusedMoEMethod)):
raise ValueError("Eplb supports only w8a8_dynamic quantization.") raise ValueError("Eplb supports only w8a8_dynamic quantization.")