From 13424fcf75875669169a6e2e91e1d2b2177160d4 Mon Sep 17 00:00:00 2001
From: ginnoir <ginnoir@users.noreply.github.com>
Date: Fri, 26 Jun 2026 16:45:33 -0500
Subject: [PATCH] fix(llm): override-kv context_length=65536 so slot isn't
 capped to 32k

llama-server caps the slot to the GGUF training context (32768) and ignores the
YaRN-extended size, leaving per-seq context at 32k. Raise qwen2.context_length
metadata to 65536 so the full window is served per request.

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 84a4246..3721c3e 100644
--- a/stacks/llm/docker-compose.yml
+++ b/stacks/llm/docker-compose.yml
@@ -44,6 +44,8 @@ services:
       - "2"
       - "--yarn-orig-ctx"
       - "32768"
+      - "--override-kv"
+      - "qwen2.context_length=int:65536"
       - "--flash-attn"
       - "on"
       - "--cache-type-k"