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

[Hardware][Intel GPU] Add v1 Intel GPU support with Flash attention backend. (#19560)

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2025-06-27 00:27:18 +08:00
committed by GitHub
parent 0bceac9810
commit b69781f107
10 changed files with 393 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@@ -28,4 +28,5 @@ docker run \
sh -c '
VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m
VLLM_USE_V1=0 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m -tp 2
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
'