perf: let midnight rose scale to zero (#86)

OpenRouterTeam · Apr 4, 2024 · e0c3077 · e0c3077
1 parent 7301ae2
commit e0c3077
Showing 1 changed file with 0 additions and 1 deletion.
diff --git a/modal/runner/containers/vllm_unified.py b/modal/runner/containers/vllm_unified.py
@@ -176,7 +176,6 @@ def __init__(self):
     model_name=_midnight_rose,
     gpu=modal.gpu.H100(count=1),
     concurrent_inputs=4,
-    keep_warm=1,
     max_containers=1,
     quantization="GPTQ",
 )