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

[Doc]: fix typos in Python comments (#24042)

Browse Source 
Signed-off-by: Didier Durand <durand.didier@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Didier Durand
2025-09-02 04:07:45 +02:00
committed by GitHub
parent a344a5aa0a
commit 0235103cbb
12 changed files with 14 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/layers/quantization/utils/quant_utils.py
View File

@@ -116,7 +116,7 @@ def _normalize_quant_group_shape(x: torch.Tensor, group_shape: GroupShape):
# then we would expand a to:
# a = [[1, 1, 2, 2],
# [3, 3, 4, 4]]
# NOTE this function this function does not explicitly broadcast dimensions
# NOTE this function does not explicitly broadcast dimensions
# with an extent of 1, since this can be done implicitly by pytorch
def group_broadcast(t, shape):
for i, s in enumerate(shape):