194c87f53c
- Node Worker: replace swapper_vision with ollama_vision (direct Ollama API) - Node Worker: add NATS subjects for stt/tts/image (stubs ready) - Node Worker: remove SWAPPER_URL dependency from config - Router: vision calls go directly to Ollama /api/generate with images - Router: local LLM calls go directly to Ollama /api/generate - Router: add OLLAMA_URL and PREFER_NODE_WORKER=true feature flag - Router: /v1/models now uses NCS global capabilities pool - NCS: SWAPPER_URL="" -> skip Swapper probing (status=disabled) - Swapper configs: remove all hardcoded model lists, keep only runtime URLs, timeouts, limits - docker-compose.node1.yml: add OLLAMA_URL, PREFER_NODE_WORKER for router; SWAPPER_URL= for NCS; remove swapper-service from node-worker depends_on - docker-compose.node2-sofiia.yml: same changes for NODA2 Swapper service still runs but is NOT in the critical inference path. Source of truth for models is now NCS -> Ollama /api/tags. Made-with: Cursor
38 lines
761 B
YAML
38 lines
761 B
YAML
# Swapper Configuration for Node #3 (AI/ML Workstation)
|
|
# Threadripper PRO + RTX 3090 24GB — GPU-intensive workloads
|
|
#
|
|
# NOTE: Swapper is now a runtime gateway / executor only.
|
|
# Source of truth for models is NCS (Node Capabilities Service).
|
|
# No hardcoded model lists.
|
|
|
|
node_id: noda3
|
|
|
|
runtimes:
|
|
ollama:
|
|
url: http://localhost:11434
|
|
timeout: 300
|
|
comfyui:
|
|
url: http://127.0.0.1:8188
|
|
|
|
limits:
|
|
llm_concurrency: 2
|
|
vision_concurrency: 1
|
|
max_concurrent_models: 2
|
|
model_swap_timeout: 300
|
|
|
|
timeouts:
|
|
llm_ms: 120000
|
|
vision_ms: 180000
|
|
image_gen_ms: 600000
|
|
|
|
gpu:
|
|
enabled: true
|
|
metal_acceleration: false
|
|
auto_unload_on_oom: true
|
|
vram_threshold_gb: 22
|
|
|
|
storage:
|
|
models_dir: /app/models
|
|
cache_dir: /app/cache
|
|
swap_dir: /app/swap
|