k3s: llama.cpp-Server als Deployments (Task 6.1) · 986f1116fe - cluster-knaster - Mindboost's Gitea: Git with a cup of sound

k3s: llama.cpp-Server als Deployments (Task 6.1)

ci / test (push) Failing after 22s

Details

Ein Pod je GPU-VM (Embed+Rerank bzw. Chat), Host-Netz mit den Ports aus dem
Compose, P2000 fest per UUID (NVIDIA_VISIBLE_DEVICES). Das Device Plugin
vergibt nur noch Index 0 (M4000). Rolle gpu-llamacpp: gemeinsame Vorbereitung
(prepare.yml), k3s.yml mit Image-Import und Compose-Stopp; gpu-llamacpp.yml
bricht ohne -e llamacpp_compose=true ab.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

This commit is contained in:

Robert Rapp

2026-10-19 17:27:23 +02:00

co-authored by

Claude Opus 5.5

parent 24f4066aaf

commit 986f1116fe

9 changed files with 278 additions and 37 deletions

									
										deploy/k8s/llamacpp/namespace.yaml
									
		+6
		
												View File
												
				@@ -0,0 +1,6 @@

				apiVersion: v1

				kind: Namespace

				metadata:

				  name: knaster

				  labels:

				    knaster.app: llamacpp

k3s: llama.cpp-Server als Deployments (Task 6.1) ci / test (push) Failing after 22s Details

k3s: llama.cpp-Server als Deployments (Task 6.1)

ci / test (push) Failing after 22s

Details