xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-09 17:35:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] Fix misleading ROCm warning (#19486)

Browse Source 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
This commit is contained in:
Jee Jee Li 2025-06-12 00:12:10 +08:00 committed by GitHub
parent 89b0f84e17
commit 04a55612dd
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

7
vllm/attention/ops/triton_flash_attention.py
View File

@ -25,9 +25,14 @@ Not currently supported:
import torch
from vllm.platforms import current_platform
from vllm.platforms.rocm import on_gfx1x
from vllm.triton_utils import tl, triton
# Avoid misleading ROCm warning.
if current_platform.is_rocm():
from vllm.platforms.rocm import on_gfx1x
else:
on_gfx1x = lambda *args, **kwargs: False
torch_dtype: tl.constexpr = torch.float16