@@ -62,7 +62,8 @@ echo "Results will be stored in: $RESULTS_DIR"
62
62
echo "--- Installing Python dependencies ---"
63
63
python3 -m pip install --progress-bar off git+https://github.com/thuml/depyf.git \
64
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
66
67
echo "--- Python dependencies installed ---"
67
68
export VLLM_USE_V1=1
68
69
export VLLM_XLA_CHECK_RECOMPILATION=1
@@ -127,39 +128,17 @@ run_and_track_test() {
127
128
}
128
129
129
130
# --- Actual Test Execution ---
130
- run_and_track_test 0 "test_perf.py" \
131
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_perf.py"
132
- run_and_track_test 1 "test_compilation.py" \
133
- "python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_compilation.py"
134
- run_and_track_test 2 "test_basic.py" \
135
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_basic.py"
136
- run_and_track_test 3 "test_accuracy.py::test_lm_eval_accuracy_v1_engine" \
137
- "python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/test_accuracy.py::test_lm_eval_accuracy_v1_engine"
138
- run_and_track_test 4 "test_quantization_accuracy.py" \
139
- "python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_quantization_accuracy.py"
140
- run_and_track_test 5 "examples/offline_inference/tpu.py" \
141
- "python3 /workspace/vllm/examples/offline_inference/tpu.py"
142
- run_and_track_test 6 "test_tpu_model_runner.py" \
143
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/worker/test_tpu_model_runner.py"
144
- run_and_track_test 7 "test_sampler.py" \
145
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_sampler.py"
146
- run_and_track_test 8 "test_topk_topp_sampler.py" \
147
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_topk_topp_sampler.py"
148
- run_and_track_test 9 "test_multimodal.py" \
149
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_multimodal.py"
150
- run_and_track_test 10 "test_pallas.py" \
151
- "python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_pallas.py"
152
- 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
- run_and_track_test 12 "test_moe_pallas.py" \
131
+ run_and_track_test 1 "test_struct_output_generate.py" \
132
+ "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\""
133
+ run_and_track_test 2 "test_moe_pallas.py" \
155
134
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
156
- run_and_track_test 13 "test_lora.py" \
135
+ run_and_track_test 3 "test_lora.py" \
157
136
"VLLM_XLA_CHECK_RECOMPILATION=0 python3 -m pytest -s -v /workspace/vllm/tests/tpu/lora/test_lora.py"
158
- run_and_track_test 14 "test_tpu_qkv_linear.py" \
137
+ run_and_track_test 4 "test_tpu_qkv_linear.py" \
159
138
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_tpu_qkv_linear.py"
160
- run_and_track_test 15 "test_spmd_model_weight_loading.py" \
139
+ run_and_track_test 5 "test_spmd_model_weight_loading.py" \
161
140
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_spmd_model_weight_loading.py"
162
- run_and_track_test 16 "test_kv_cache_update_kernel.py" \
141
+ run_and_track_test 6 "test_kv_cache_update_kernel.py" \
163
142
"python3 -m pytest -s -v /workspace/vllm/tests/v1/tpu/test_kv_cache_update_kernel.py"
164
143
165
144
# After all tests have been attempted, exit with the overall status.
0 commit comments