xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 11:17:07 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Core][MM] Use non-blocking CPU-GPU copy of multimodal data (#28141)

Browse Source 
Signed-off-by: Lukas Geiger <lukas.geiger94@gmail.com>
This commit is contained in:
Lukas Geiger 2025-11-06 04:05:12 +00:00 committed by GitHub
parent 43ecd0a900
commit 80679f108f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 3 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
vllm/multimodal/utils.py
View File

@ -444,7 +444,9 @@ def group_mm_kwargs_by_modality(
if device is not None:
mm_kwargs_group = json_map_leaves(
lambda x: x.to(device=device) if isinstance(x, torch.Tensor) else x,
lambda x: x.to(device=device, non_blocking=True)
if isinstance(x, torch.Tensor)
else x,
mm_kwargs_group,
)
else: