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 14, 05:30 UTC
[XPU] add missing dependency tblib for XPU CI (#24639)
Signed-off-by: Fanli Lin <fanli.lin@intel.com>
Fanli Lin committed
Sep 11, 2025 at 19:22 UTC
0cd72a7b72ed5021e148eb44d6ca41e0daff132c
1 file changed
+1
.buildkite/scripts/hardware_ci/run-xpu-test.sh
+1
@@ -30,6 +30,7 @@ docker run \
30
bash -c '
31
set -e
32
echo $ZE_AFFINITY_MASK
33
+ pip install tblib==3.1.0
34
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager
35
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 -O3 -O.cudagraph_mode=NONE
36
python3 examples/offline_inference/basic/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend ray