From 74791105b3927d5d1883cbcf424176e5dd70c1fe Mon Sep 17 00:00:00 2001
From: ginnoir <ginnoir@users.noreply.github.com>
Date: Fri, 26 Jun 2026 16:42:41 -0500
Subject: [PATCH] fix(llm): --parallel 1 so a single request gets the full 64k
 context

With the default 4 slots, llama-server splits ctx into 32k per sequence, which
fails Hermes' 64K minimum. One slot serves the full 65536 per request (serial
agent use; concurrent calls queue).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 stacks/llm/docker-compose.yml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/stacks/llm/docker-compose.yml b/stacks/llm/docker-compose.yml
index 743e5b5..84a4246 100644
--- a/stacks/llm/docker-compose.yml
+++ b/stacks/llm/docker-compose.yml
@@ -32,6 +32,8 @@ services:
       - "/models/Qwen2.5-14B-Instruct-Q4_K_M.gguf"
       - "--alias"
       - "qwen2.5-14b-instruct"
+      - "--parallel"
+      - "1"
       - "-ngl"
       - "99"
       - "--ctx-size"