A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 02:15 UTC
[Bugfix] Fix OOM in language generation test (#20814)
Signed-off-by: Isotr0py <2037008807@qq.com> Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Isotr0py committed
Jul 12, 2025 at 02:21 UTC
0d21b2664c82448bbea1464496063f9b99cf61ea
1 file changed
+1
-1
tests/models/language/generation/test_common.py
+1
-1
@@ -90,7 +90,7 @@ AITER_MODEL_LIST = [
90
marks=[pytest.mark.core_model],
91
),
92
pytest.param(
93
- "Qwen/Qwen1.5-MoE-A2.7B-Chat",
93
+ "allenai/OLMoE-1B-7B-0924-Instruct",
94
marks=[pytest.mark.cpu_model],
95
)
96
])