From 6b8a1f341a477989fd503e8e0d92cdedf5ec5855 Mon Sep 17 00:00:00 2001 From: Marc Blatter Date: Wed, 29 Jul 2026 09:18:17 +0000 Subject: [PATCH] enable-prefix-caching --- composte-hermes.yml | 2 ++ 1 file changed, 2 insertions(+) diff --git a/composte-hermes.yml b/composte-hermes.yml index 7957454..8f58b35 100644 --- a/composte-hermes.yml +++ b/composte-hermes.yml @@ -32,6 +32,8 @@ services: - --served-model-name=qwen3-14b-awq - --enable-auto-tool-choice - --tool-call-parser=hermes + - --enable-prefix-caching # 2x RTX 3060 (12 GB) + - --prefix-cache-threshold=0.8 # 24 GB VRAM healthcheck: test: ["CMD", "curl", "-f", "http://localhost:8005/health"] interval: 30s