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, 23:45 UTC
[TPU][TEST] Fix the downloading issue in TPU v1 test 11. (#21418)
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
QiliangCui committed
Jul 23, 2025 at 11:29 UTC
14bf19e39f601163265b7c7d58d972b8a83d8896
1 file changed
+3
-2
.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
+3
-2
@@ -62,7 +62,8 @@ echo "Results will be stored in: $RESULTS_DIR"
62
echo "--- Installing Python dependencies ---"
63
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
64
&& python3 -m pip install --progress-bar off pytest pytest-asyncio tpu-info \
65
- && python3 -m pip install --progress-bar off lm_eval[api]==0.4.4
65
+ && python3 -m pip install --progress-bar off lm_eval[api]==0.4.4 \
66
+ && python3 -m pip install --progress-bar off hf-transfer
67
echo "--- Python dependencies installed ---"
68
export VLLM_USE_V1=1
69
export VLLM_XLA_CHECK_RECOMPILATION=1
@@ -150,7 +151,7 @@ run_and_track_test 9 "test_multimodal.py" \
151
run_and_track_test 10 "test_pallas.py" \
152
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_pallas.py"
153
run_and_track_test 11 "test_struct_output_generate.py" \
153
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
154
+ "HF_HUB_DISABLE_XET=1 python3 -m pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
155
run_and_track_test 12 "test_moe_pallas.py" \
156
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
157
run_and_track_test 13 "test_lora.py" \