diff --git a/computility-run.yaml b/computility-run.yaml index 0d4bb511..9c15aac6 100644 --- a/computility-run.yaml +++ b/computility-run.yaml @@ -32,6 +32,8 @@ command: - --enforce-eager - --dtype - half + - --num-gpu-blocks-override + - '4000' env: - name: VLLM_ENGINE_ITERATION_TIMEOUT_S value: 3600