xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-10 07:15:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

Temporarily suspend google/gemma-3-1b-it. (#20722)

Browse Source 
Signed-off-by: Qiliang Cui <derrhein@gmail.com>
This commit is contained in:
QiliangCui 2025-07-11 04:21:26 -07:00 committed by GitHub
parent cbd14ed561
commit b4f0b5f9aa
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 6 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
tests/entrypoints/llm/test_accuracy.py
View File

@ -69,6 +69,12 @@ def test_lm_eval_accuracy_v1_engine(model, monkeypatch: pytest.MonkeyPatch):
more_args = None more_args = None
if current_platform.is_tpu(): if current_platform.is_tpu():
# Limit compilation time for TPU V1 # Limit compilation time for TPU V1
if model == "google/gemma-3-1b-it":
pytest.skip(
"Temporarily disabled due to test failures"
"(timeout or accuracy mismatch). Re-enable once fixed.")
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)