xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-17 11:35:49 +08:00
Code Issues Packages Projects Releases Wiki Activity

[CI/Build] do not enforce precompilation on tpu ci tests (#25992)

Browse Source 
Signed-off-by: Xiang Si <sixiang@google.com>
Signed-off-by: yewentao256 <zhyanwentao@126.com>
This commit is contained in:
Xiang Si 2025-10-03 06:38:42 -07:00 committed by yewentao256
parent fac9b430ec
commit d8b1f9ccc3
1 changed files with 1 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tests/v1/entrypoints/llm/test_struct_output_generate.py
View File

@ -123,13 +123,10 @@ def test_structured_output(
if current_platform.is_tpu() and speculative_config: if current_platform.is_tpu() and speculative_config:
pytest.skip("TPU does not support speculative decoding") pytest.skip("TPU does not support speculative decoding")
# Don't use eager execution on TPUs because we want to test for no
# recompilation at runtime
enforce_eager = bool(not current_platform.is_tpu())
# Use a single LLM instance for several scenarios to # Use a single LLM instance for several scenarios to
# speed up the test suite. # speed up the test suite.
llm = LLM(model=model_name, llm = LLM(model=model_name,
enforce_eager=enforce_eager, enforce_eager=True,
max_model_len=1024, max_model_len=1024,
structured_outputs_config=dict(backend=backend, structured_outputs_config=dict(backend=backend,
disable_any_whitespace=backend disable_any_whitespace=backend