Skip to content

GitLab

Commit 0c060491 authored by zhuwenwen's avatar zhuwenwen
Browse files

update topk_softmax

parent 03cdc9be
Hide whitespace changes
Inline Side-by-side
Showing with 1 addition and 1 deletion
vllm/model_executor/layers/fused_moe/fused_moe.py
View file @ 0c060491
...@@ -1234,7 +1234,7 @@ def vllm_topk_softmax(topk_weights: torch.Tensor, topk_indices: torch.Tensor, ...@@ -1234,7 +1234,7 @@ def vllm_topk_softmax(topk_weights: torch.Tensor, topk_indices: torch.Tensor,
topk_indices, topk_indices,
token_expert_indices, token_expert_indices,
gating_output, gating_output,
Is_renormalize = True, True,
) )
else: else:
ops.topk_softmax( ops.topk_softmax(
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment