Merge branch 'v0.11.0-dev-fth' into 'v0.11.0-dev'

适配block-wise fp8接口

See merge request dcutoolkit/deeplearing/vllm!366

vllm/model_executor/layers/quantization/fp8.py

@@ -917,7 +917,7 @@ class Fp8MoEMethod(FusedMoEMethodBase):
         logical_to_physical_map: Optional[torch.Tensor] = None,
         logical_replica_count: Optional[torch.Tensor] = None,
         topk_weights: Optional[torch.Tensor] = None,
-        topk_ids: Optional[torch.Tensor] = None,
+        topk_ids: Optional[torch.Tensor] = None,**_,
     ) -> Union[torch.Tensor, tuple[torch.Tensor, torch.Tensor]]:
 
         if enable_eplb: