Skip to content

[Bugfix] Fix precision issues in moe_mlp (vllm-ascend main) #5025

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wangxiyuan merged 1 commit into from
Dec 16, 2025
+1 −1
Merged

[Bugfix] Fix precision issues in moe_mlp (vllm-ascend main) #5025

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion vllm_ascend/ops/fused_moe/moe_mlp.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,7 +46,7 @@ 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
Comment on lines 47 to 50
Copy link
Contributor

@gemini-code-assist gemini-code-assist bot Dec 15, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

high

There's a potential IndexError here if group_list is an empty tensor. Accessing group_list[0] on line 49 would cause a crash. It's good practice to handle this edge case, for example by checking if the tensor is empty before proceeding.

Suggested change
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 == 0 and dst_list_type == 1:
if not group_list.numel():
return group_list
group_diff = torch.diff(group_list)
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))
Expand Down
Loading