From 171178f7d0d675b8b5387dd0d8f66eb302518c57 Mon Sep 17 00:00:00 2001 From: Roger Oriol Date: Sun, 2 Aug 2026 11:19:26 +0200 Subject: [PATCH] change qwen parallelism to 2 --- llamacpp/deployment-qwen36-27b.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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