Folzo/Effi
Public Access
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: llm-proxy - switch d'instance llama.cpp transparent + UI :3017

Browse Source 
- Route virtuelle :3012 -> instance active (8080 Q4_K_M / 8081 IQ4_XS), etat persiste
- Alias modele qwen3.8-27b : reecriture id reel <-> alias (v1/models, chat, completions,
  embeddings, streaming SSE) -> switch transparent pour tous les harnais
- UI de gestion :3017 (statut, Activer, Tester) en page unique sans dependance ajoutee
- Fail-fast 503 (20s) si instance active arreteee, sans spam WOL
This commit is contained in:
Effi Server
2026-09-19 12:09:02 +00:00
parent cbcf349f39
commit 5fc23a562d
7 changed files with 421 additions and 41 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docker-compose.yml
+11 -1
View File
@@ -60,9 +60,10 @@ services:
# ─────────────────────────────────────────────────────────
# 2. LLM PROXY - Proxy unique vers le PC Gaming + Wake-on-LAN
# :3011 → Ollama (.11:11434)
# :3012 → llama.cpp (.11:8080)
# :3012 → llama.cpp (route virtuelle : instance active, alias qwen3.8-27b)
# :3015 → STT (.11:8200)
# :3016 → TTS (serveur local :8100, pas de WOL)
# :3017 → UI de gestion (switch d'instance llama.cpp + tests)
# Si le PC est éteint, un paquet WoL est envoyé avant l'attente.
# ─────────────────────────────────────────────────────────
llm-proxy:
@@ -77,6 +78,15 @@ services:
- WAKE_TIMEOUT=${WAKE_TIMEOUT:-300}
- SERVICE_TIMEOUT=120
- CHECK_INTERVAL=5
- LLAMACPP_A_PORT=${LLAMACPP_A_PORT:-8080}
- LLAMACPP_A_MODEL=${LLAMACPP_A_MODEL:-qwen3.8-27b}
- LLAMACPP_A_LABEL=${LLAMACPP_A_LABEL:-Q4_K_M}
- LLAMACPP_B_PORT=${LLAMACPP_B_PORT:-8081}
- LLAMACPP_B_MODEL=${LLAMACPP_B_MODEL:-qwen3.8-27b-iq4xs}
- LLAMACPP_B_LABEL=${LLAMACPP_B_LABEL:-IQ4_XS}
- DEFAULT_ACTIVE=${DEFAULT_ACTIVE:-qwen3.8-27b-iq4xs}
volumes:
- ./llm-proxy/state:/app/state
# ─────────────────────────────────────────────────────────
# 3. MCPO - Proxy outils MCP (Obsidian, etc.)