From f59fb476b8e0bb8a41e1ebe0a599a1ceb8789101 Mon Sep 17 00:00:00 2001
From: rock <locartrock@gmail.com>
Date: Wed, 16 Sep 2026 07:21:45 +0900
Subject: [PATCH] =?UTF-8?q?feat(ornith):=20bump=20context=20length=2032K?=
 =?UTF-8?q?=20=E2=86=92=2064K?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

V100-PCIE-32GB has ~12GB VRAM headroom after model weights.
ornith:35b Q4_K_M KV cache at 64K ≈ 11.8GB — fits within budget.
Model natively supports 256K but hardware caps safe limit at 64K.
---
 k8s/apps/llm-serving/ornith.yaml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/k8s/apps/llm-serving/ornith.yaml b/k8s/apps/llm-serving/ornith.yaml
index 47e3243..be9c841 100644
--- a/k8s/apps/llm-serving/ornith.yaml
+++ b/k8s/apps/llm-serving/ornith.yaml
@@ -44,7 +44,7 @@ spec:
       - name: OLLAMA_MODELS
         value: /mnt/models/ollama
       - name: OLLAMA_CONTEXT_LENGTH
-        value: '32768'
+        value: '65536'
       - name: OLLAMA_KEEP_ALIVE
         value: '-1'
       - name: OLLAMA_NUM_PARALLEL