Skip to content
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

[BugFix] fix group_topk #8430

Merged
merged 2 commits into from
Sep 13, 2024
Merged

[BugFix] fix group_topk #8430

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6564176
update group topk to return int32, not int64
dsikka Sep 12, 2024
e5bcf12
Format
dsikka Sep 12, 2024
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
4 changes: 3 additions & 1 deletion vllm/model_executor/layers/fused_moe/fused_moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -410,6 +410,7 @@ def fused_topk(

if renormalize:
topk_weights = topk_weights / topk_weights.sum(dim=-1, keepdim=True)

return topk_weights, topk_ids


Expand Down Expand Up @@ -443,7 +444,8 @@ def grouped_topk(hidden_states: torch.Tensor,

if renormalize:
topk_weights = topk_weights / topk_weights.sum(dim=-1, keepdim=True)
return topk_weights, topk_ids

return topk_weights, topk_ids.to(torch.int32)


def get_config_dtype_str(dtype: torch.dtype,
Expand Down
Loading