xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 06:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fix an error in dummy weight loading for quantization models (#18855)

Browse Source 
Signed-off-by: Chenyaaang <chenyangli@google.com>
This commit is contained in:
Chenyaaang 2025-05-29 03:07:20 -07:00 committed by GitHub
parent f274581f44
commit f8977c233f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
vllm/model_executor/model_loader/weight_utils.py
View File

@ -696,7 +696,7 @@ def initialize_dummy_weights(
# Note: We avoid using torch.rank_like as it doesn't currently
# support the generator argument.
param.copy_((high - low) *
torch.rand(*param.shape,
torch.rand(param.shape,
generator=generator,
dtype=param.dtype,
layout=param.layout,