We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent bec6523 commit e16e389Copy full SHA for e16e389
tests/singlecard/spec_decode/e2e/test_mtp_correctness.py
@@ -78,7 +78,7 @@
78
"model_name": FLOAT_MODEL,
79
80
# GPU memory utilization
81
- "gpu_memory_utilization": 0.85
+ "gpu_memory_utilization": 0.8
82
}])
83
@pytest.mark.parametrize("per_test_common_llm_kwargs", [{}])
84
@pytest.mark.parametrize("baseline_llm_kwargs", [{}])
0 commit comments