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

[Hardware][ROCM] using current_platform.is_rocm (#9642)

Browse Source 
Signed-off-by: wangshuai09 <391746016@qq.com>
This commit is contained in:
wangshuai09
2024-10-28 12:07:00 +08:00
committed by GitHub
parent 34a9941620
commit 4e2d95e372
32 changed files with 165 additions and 151 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
tests/models/decoder_only/vision_language/test_phi3v.py
View File

@@ -12,7 +12,6 @@ from vllm.multimodal import MultiModalRegistry
from vllm.multimodal.utils import rescale_image_size
from vllm.platforms import current_platform
from vllm.sequence import SampleLogprobs
from vllm.utils import is_hip
from ....conftest import (IMAGE_ASSETS, HfRunner, PromptImageInput, VllmRunner,
_ImageAssets)
@@ -56,7 +55,7 @@ if current_platform.is_cpu():
# ROCm Triton FA can run into shared memory issues with these models,
# use other backends in the meantime
# FIXME (mattwong, gshtrasb, hongxiayan)
if is_hip():
if current_platform.is_rocm():
os.environ["VLLM_USE_TRITON_FLASH_ATTN"] = "0"