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

Remove unused code in fused_moe.py (#2805)

Browse Source 
### What this PR does / why we need it?
line 408 already declared mc2_mask ,  remove duplicated unused code

### Does this PR introduce _any_ user-facing change?
no

### How was this patch tested?
CI passed with existing test.

- vLLM version: v0.10.1.1
- vLLM main:
60f0843ef8

Signed-off-by: machenglong <machenglong_yewu@cmss.chinamobile.com>
This commit is contained in:
machenglong2025
2025-09-08 20:05:19 +08:00
committed by GitHub
parent d51694a77b
commit 1a82b16355
1 changed files with 0 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/ops/fused_moe.py
View File

@@ -413,8 +413,6 @@ class AscendFusedMoE(FusedMoE):
# When all_reduce_merge is in progress, shared_experts does not do all_reduce in mlp, but waits until shared_experts+router_experts are completed before doing all_reduce
shared_hidden_states = shared_experts(hidden_states)
mc2_mask = forward_context.mc2_mask
enable_sp = _metadata_for_padding is not None and _metadata_for_padding.not_dummy_and_is_prefill
tp_size = get_tensor_model_parallel_world_size()
if enable_sp: