biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc]: fix typos in Python comments (#24294)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
Didier Durand
2025-09-06 04:41:12 +02:00
committed by GitHub
parent 35efa70297
commit 35bf193864
12 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/fused_moe/fused_moe.py
View File

@@ -534,7 +534,7 @@ def invoke_fused_moe_kernel(A: torch.Tensor,
EM = sorted_token_ids.size(0)
if A.size(0) < config["BLOCK_SIZE_M"]:
# optimize for small batch_size.
# We assume that top_ids of each token is unique, so
# We assume that top_ids of each token is unique,
# so num_valid_experts <= batch_size <= BLOCK_SIZE_M,
# and we can skip some invalid blocks.
EM = min(sorted_token_ids.size(0),