xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-15 18:16:46 +08:00
Code Issues Packages Projects Releases Wiki Activity

[TPU][TEST] HF_HUB_DISABLE_XET=1 the test 3. (#21539)

Browse Source 
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
This commit is contained in:
QiliangCui 2025-07-24 15:33:04 -07:00 committed by GitHub
parent 2dd72d23d9
commit 07d80d7b0e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/scripts/hardware_ci/run-tpu-v1-test.sh
View File

@ -135,7 +135,7 @@ run_and_track_test 1 "test_compilation.py" \
run_and_track_test 2 "test_basic.py" \ run_and_track_test 2 "test_basic.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_basic.py" "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_basic.py"
run_and_track_test 3 "test_accuracy.py::test_lm_eval_accuracy_v1_engine" \ run_and_track_test 3 "test_accuracy.py::test_lm_eval_accuracy_v1_engine" \
"python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/test_accuracy.py::test_lm_eval_accuracy_v1_engine" "HF_HUB_DISABLE_XET=1 python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/test_accuracy.py::test_lm_eval_accuracy_v1_engine"
run_and_track_test 4 "test_quantization_accuracy.py" \ run_and_track_test 4 "test_quantization_accuracy.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py" "python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py"
run_and_track_test 5 "examples/offline_inference/tpu.py" \ run_and_track_test 5 "examples/offline_inference/tpu.py" \

3
tests/entrypoints/llm/test_accuracy.py
View File

@ -73,9 +73,6 @@ def test_lm_eval_accuracy_v1_engine(model, monkeypatch: pytest.MonkeyPatch):
if current_platform.is_tpu(): if current_platform.is_tpu():
# Limit compilation time for TPU V1 # Limit compilation time for TPU V1
# xet doesn't work well for both Qwen/Qwen3-1.7B and
# google/gemma-3-1b-it
m.setenv("HF_HUB_DISABLE_XET", "1")
more_args = "max_model_len=2048,max_num_seqs=64" more_args = "max_model_len=2048,max_num_seqs=64"
# Add TP test (if provided) # Add TP test (if provided)