From 4e2a75b10c6e804066a777f8f30006ee33e569ef Mon Sep 17 00:00:00 2001 From: Alexander Rogov Date: Tue, 14 Jul 2026 00:58:38 +0300 Subject: [PATCH] smaller cache --- manifests/llama/rp.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/manifests/llama/rp.yaml b/manifests/llama/rp.yaml index 1273e34..c54b8e6 100644 --- a/manifests/llama/rp.yaml +++ b/manifests/llama/rp.yaml @@ -93,7 +93,7 @@ spec: # performance tuning - "--ctx-size" - - "32768" + - "16386" - "--parallel" - "1"