From e56d29528ff3d3826528e9b869089770733582d5 Mon Sep 17 00:00:00 2001 From: HaimKortovich Date: Thu, 7 May 2026 11:28:09 -0500 Subject: [PATCH] set cache reuse to 1 --- clusters/k3s-dgx/nim-service/qwen.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/clusters/k3s-dgx/nim-service/qwen.yaml b/clusters/k3s-dgx/nim-service/qwen.yaml index 176b1c0..eadb103 100644 --- a/clusters/k3s-dgx/nim-service/qwen.yaml +++ b/clusters/k3s-dgx/nim-service/qwen.yaml @@ -46,7 +46,7 @@ spec: - name: NIM_MAX_MODEL_LEN value: "32768" - name: NIM_ENABLE_KV_CACHE_REUSE - value: "true" + value: "1" image: repository: nvcr.io/nim/qwen/qwen3-32b-dgx-spark tag: "1.1.0-variant"