From 89516d9cc3e1981890105d1834e176c50cc61f66 Mon Sep 17 00:00:00 2001 From: Roger Oriol Date: Sun, 2 Aug 2026 12:33:15 +0200 Subject: [PATCH] upgrade qwen 4b context to 65k --- llamacpp/deployment-qwen35-4b.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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