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
[CI/Build] Update compressed tensor test path to fix CPU CI (#27068)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
Li, Jiang committed
Oct 17, 2025 at 13:34 UTC
5550ff9c25b8d6d2ba35572883602423f74fb9bf
1 file changed
+1
-1
.buildkite/scripts/hardware_ci/run-cpu-test.sh
+1
-1
@@ -70,7 +70,7 @@ function cpu_tests() {
70
docker exec cpu-test-"$NUMA_NODE" bash -c "
71
set -e
72
pytest -x -s -v \
73
- tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs[False-10-32-neuralmagic/Llama-3.2-1B-quantized.w8a8]"
73
+ tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs"
74
75
# Note: disable it until supports V1
76
# Run AWQ test