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 15, 19:45 UTC
Fix run_tpu_test (#14641)
Signed-off-by: <ricliu@google.com> Signed-off-by: Richard Liu <ricliu@google.com>
Richard Liu committed
Mar 11, 2025 at 14:14 UTC
d374f04a337dbd4aab31484b6fa2d4a5f20c2116
1 file changed
-1
.buildkite/run-tpu-test.sh
-1
@@ -19,7 +19,6 @@ docker run --privileged --net host --shm-size=16G -it \
19
vllm-tpu /bin/bash -c "python3 -m pip install git+https://github.com/thuml/depyf.git \
20
&& python3 -m pip install pytest \
21
&& python3 -m pip install lm_eval[api]==0.4.4 \
22
- && pytest -v -s /workspace/vllm/tests/entrypoints/openai/test_accuracy.py \
22
&& pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
23
&& python3 /workspace/vllm/tests/tpu/test_compilation.py \
24
&& python3 /workspace/vllm/tests/tpu/test_quantization_accuracy.py \