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

Revert "[V0 deprecation] Remove V0 CPU/XPU/TPU backends (#20412)"
Some checks failed
Create Release / Create Release (push) Has been cancelled
Details

Browse Source 
This reverts commit e202dd2736.
This commit is contained in:
simon-mo
2025-07-06 14:02:36 -07:00
parent c18b3b8e8b
commit a5dd03c1eb
20 changed files with 5034 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
.buildkite/scripts/hardware_ci/run-cpu-test.sh
View File

@@ -66,10 +66,10 @@ function cpu_tests() {
tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_dynamic_per_token"
# Run AWQ test
# docker exec cpu-test-"$NUMA_NODE" bash -c "
# set -e
# VLLM_USE_V1=0 pytest -s -v \
# tests/quantization/test_ipex_quant.py"
docker exec cpu-test-"$NUMA_NODE" bash -c "
set -e
VLLM_USE_V1=0 pytest -s -v \
tests/quantization/test_ipex_quant.py"
# Run chunked-prefill and prefix-cache test
docker exec cpu-test-"$NUMA_NODE" bash -c "

2
.buildkite/scripts/hardware_ci/run-xpu-test.sh
View File

@@ -26,5 +26,7 @@ docker run \
--name "${container_name}" \
"${image_name}" \
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
'