deploy: Dockerfile, Compose pro Rolle, LiteLLM, Prometheus/Alertmanager, Canary-Prober, n8n-Workflows

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-12 00:51:31 +02:00
parent 4cbe313c62
commit cb5a413169
28 changed files with 1731 additions and 9 deletions
@@ -0,0 +1,8 @@
+LLAMACPP_REF=b6000
+CUDA_VERSION=12.4.0
+CUDA_DOCKER_ARCH=52;61
+MODELS_DIR=/srv/models
+EMBED_GGUF=Qwen3-Embedding-0.6B-Q8_0.gguf
+EMBED_POOLING=last
+RERANK_GGUF=bge-reranker-v2-m3-Q8_0.gguf
+CHAT_GGUF=Qwen3-4B-Q4_K_M.gguf