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

[Bugfix]Fix precision issues in moe_mlp (vllm-ascend v0.11.0-dev) (#5023)

Browse Source 
### What this PR does / why we need it?
Use group_list[0] to replace group_diff[0] in function
"cumsum_group_list" (moe_mlp.py).
The purpose is to modify it to the correct logic of converting cumsum to
count.

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

Signed-off-by: tanqingshan (A)  <50050625@china.huawei.com>
Co-authored-by: tanqingshan (A) <50050625@china.huawei.com>
This commit is contained in:
Clorist33
2025-12-16 08:40:03 +08:00
committed by GitHub
parent 87c0cfafa3
commit 2b5b309133
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/ops/moe/moe_mlp.py
View File

@@ -41,7 +41,7 @@ def cumsum_group_list(group_list: torch.Tensor,
return group_list.cumsum(dim=0)
if src_list_type == 0 and dst_list_type == 1:
group_diff = torch.diff(group_list)
new_group = torch.cat([group_diff[0].unsqueeze(0), group_diff], dim=0)
new_group = torch.cat([group_list[0].unsqueeze(0), group_diff], dim=0)
return new_group
if src_list_type == 2 and dst_list_type == 0:
experts = pad(group_list[:, 0], (1, 0))