xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-29 12:47:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

Re-enable Xet on TPU tests now that hf_xet has been updated (#22666)

Browse Source 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
This commit is contained in:
Harry Mellor 2025-08-12 03:54:40 +01:00 committed by GitHub
parent 9b94d6ec8f
commit 839ab00349
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 2 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
.buildkite/scripts/hardware_ci/run-tpu-v1-test-part2.sh
View File

@ -128,7 +128,7 @@ run_and_track_test() {
# --- Actual Test Execution ---
run_and_track_test 1 "test_struct_output_generate.py" \
"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\""
"python3 -m pytest -s -v /workspace/vllm/tests/v1/entrypoints/llm/test_struct_output_generate.py -k \"not test_structured_output_with_reasoning_matrices\""
run_and_track_test 2 "test_moe_pallas.py" \
"python3 -m pytest -s -v /workspace/vllm/tests/tpu/test_moe_pallas.py"
run_and_track_test 3 "test_lora.py" \

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

@ -134,7 +134,7 @@ run_and_track_test 1 "test_compilation.py" \
run_and_track_test 2 "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" \
"HF_HUB_DISABLE_XET=1 python3 -m pytest -s -v /workspace/vllm/tests/entrypoints/llm/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"
run_and_track_test 4 "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" \

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

@ -96,9 +96,6 @@ def test_lm_eval_accuracy_v1_engine_fp8_kv_cache(
more_args = None
if current_platform.is_tpu():
# Limit compilation time for TPU V1
# xet doesn't work well for Qwen/Qwen3-1.7B
m.setenv("HF_HUB_DISABLE_XET", "1")
more_args = "max_model_len=2048,max_num_seqs=128,kv_cache_dtype=fp8"
# Add TP test (if provided)