diff --git a/llamacpp/deployment-qwen36-27b.yaml b/llamacpp/deployment-qwen36-27b.yaml index ec9f8b3..f1faeb0 100644 --- a/llamacpp/deployment-qwen36-27b.yaml +++ b/llamacpp/deployment-qwen36-27b.yaml @@ -71,7 +71,7 @@ spec: - -c - "131072" - -np - - "1" + - "2" - --cont-batching - --cache-type-k - q8_0