feat: add BGE embedding service and reorganize supervisor groups
All checks were successful
Build and Push RunPod Docker Image / build-and-push (push) Successful in 14s

- Add vLLM embedding server for BAAI/bge-large-en-v1.5 (port 8002)
- Reorganize supervisor into two logical groups:
  - comfyui-services: comfyui, webdav-sync
  - vllm-services: vllm-qwen, vllm-llama, vllm-embedding
- Update arty.yml service management scripts for new group structure
- Add individual service control scripts for all vLLM models

Note: Embedding server currently uses placeholder implementation
For production use, switch to sentence-transformers or native vLLM embedding mode

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
2025-11-25 06:32:01 +01:00
parent e12a8add61
commit 5af3eeb333
3 changed files with 274 additions and 25 deletions

View File

@@ -73,6 +73,23 @@ environment=HF_HOME="../huggingface_cache",HF_TOKEN="%(ENV_HF_TOKEN)s"
priority=201
stopwaitsecs=30
# vLLM BGE Embedding Server (Port 8002)
[program:vllm-embedding]
command=vllm/venv/bin/python vllm/server_embedding.py
directory=.
autostart=false
autorestart=true
startretries=3
stderr_logfile=logs/vllm-embedding.err.log
stdout_logfile=logs/vllm-embedding.out.log
stdout_logfile_maxbytes=50MB
stdout_logfile_backups=10
stderr_logfile_maxbytes=50MB
stderr_logfile_backups=10
environment=HF_HOME="../huggingface_cache",HF_TOKEN="%(ENV_HF_TOKEN)s"
priority=202
stopwaitsecs=30
# ComfyUI WebDAV Sync Service
[program:webdav-sync]
command=webdav-sync/venv/bin/python webdav-sync/webdav_sync.py
@@ -90,6 +107,10 @@ environment=WEBDAV_URL="%(ENV_WEBDAV_URL)s",WEBDAV_USERNAME="%(ENV_WEBDAV_USERNA
priority=150
stopwaitsecs=10
[group:ai-services]
programs=comfyui,vllm-qwen,vllm-llama,webdav-sync
priority=999
[group:comfyui-services]
programs=comfyui,webdav-sync
priority=100
[group:vllm-services]
programs=vllm-qwen,vllm-llama,vllm-embedding
priority=200