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

[XPU] support Triton Attention backend on Intel GPU (#24149)

Browse Source 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
This commit is contained in:
Kunshang Ji
2025-09-04 20:41:08 +08:00
committed by GitHub
parent 2b30afa442
commit 16ded21eeb
5 changed files with 49 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@@ -30,10 +30,11 @@ docker run \
bash -c '
set -e
echo $ZE_AFFINITY_MASK
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 -O3 -O.cudagraph_mode=NONE
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
VLLM_USE_V1=1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 -O3 -O.cudagraph_mode=NONE
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp
VLLM_ATTENTION_BACKEND=TRITON_ATTN_VLLM_V1 python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
cd tests
pytest -v -s v1/core
pytest -v -s v1/engine