[CI][TPU] Temporarily Disable Quant Test on TPU (#15649)

Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
This commit is contained in:
Robert Shaw
2025-03-27 22:45:05 -04:00
committed by GitHub
parent b4245a48df
commit 8a49eea74b
2 changed files with 5 additions and 7 deletions

View File

@@ -28,15 +28,16 @@ docker run --privileged --net host --shm-size=16G -it \
&& echo TEST_3 \
&& pytest -v -s /workspace/vllm/tests/entrypoints/llm/test_accuracy.py::test_lm_eval_accuracy_v1_engine \
&& echo TEST_4 \
&& pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py \
&& echo TEST_5 \
&& python3 /workspace/vllm/examples/offline_inference/tpu.py \
&& echo TEST_6 \
&& echo TEST_5 \
&& pytest -s -v /workspace/vllm/tests/tpu/worker/test_tpu_model_runner.py \
&& echo TEST_7 \
&& echo TEST_6 \
&& pytest -s -v /workspace/vllm/tests/v1/tpu/test_sampler.py" \
# TODO: This test fails because it uses RANDOM_SEED sampling
# && VLLM_USE_V1=1 pytest -v -s /workspace/vllm/tests/tpu/test_custom_dispatcher.py \
# TODO: Re-enable this after fixing recompilation in quantization.
# && echo TEST_4 \
# && pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py \