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 17, 03:00 UTC
[CI/Build] Make Marlin Tests Green (#3753)
Robert Shaw committed
Mar 30, 2024 at 21:18 UTC
563c1d7ec56aa0f9fdc28720f3517bf9297f5476
1 file changed
+1
-1
tests/models/test_marlin.py
+1
-1
@@ -47,7 +47,7 @@ model_pairs = [
47
@pytest.mark.parametrize("model_pair", model_pairs)
48
@pytest.mark.parametrize("dtype", ["half"])
49
@pytest.mark.parametrize("max_tokens", [32])
50
-@pytest.mark.parametrize("num_logprobs", [3])
50
+@pytest.mark.parametrize("num_logprobs", [5])
51
def test_models(
52
vllm_runner,
53
example_prompts,