diff --git a/llamacpp/deployment-qwen35-4b.yaml b/llamacpp/deployment-qwen35-4b.yaml index 90240fe..398ed26 100644 --- a/llamacpp/deployment-qwen35-4b.yaml +++ b/llamacpp/deployment-qwen35-4b.yaml @@ -68,7 +68,7 @@ spec: - -ngl - "999" - -c - - "8192" + - "65536" - -np - "1" - --cont-batching