A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 10, 21:30 UTC
[CI/Build][CPU] Update CPU CI test cases (#31466)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Dec 29, 2025 at 14:17 UTC
17347daaa24ee033e3a5403fb154c64c5b967bd5
1 file changed
+1
-1
.buildkite/scripts/hardware_ci/run-cpu-test.sh
+1
-1
@@ -84,7 +84,7 @@ function cpu_tests() {
84
docker exec cpu-test-"$NUMA_NODE" bash -c "
85
set -e
86
pytest -x -s -v \
87
- tests/lora/test_qwen2vl.py"
87
+ tests/lora/test_qwenvl.py"
88
89
# online serving: tp+pp
90
docker exec cpu-test-"$NUMA_NODE" bash -c '