ilia
7c633a02ed
- Added .cursorrules for project guidelines and context - Created README.md for project overview and goals - Established ARCHITECTURE.md for architectural documentation - Set up tickets directory with initial ticket management files - Included .gitignore to manage ignored files and directories This commit lays the foundation for the Atlas project, ensuring a clear structure for development and collaboration.
53 lines
1.2 KiB
Markdown
53 lines
1.2 KiB
Markdown
# Ticket: Stand Up 1050 LLM Service
|
|
|
|
## Ticket Information
|
|
|
|
- **ID**: TICKET-022
|
|
- **Title**: Stand Up 1050 LLM Service
|
|
- **Type**: Feature
|
|
- **Priority**: High
|
|
- **Status**: Backlog
|
|
- **Track**: LLM Infra
|
|
- **Milestone**: Milestone 2 - Voice Chat MVP
|
|
- **Created**: 2024-01-XX
|
|
|
|
## Description
|
|
|
|
Set up LLM service on 1050:
|
|
- Smaller model, lower concurrency
|
|
- Persistent process managed via systemd/docker
|
|
- Expose HTTP/gRPC API
|
|
- Support function-calling/tool use
|
|
- Load selected family agent model
|
|
|
|
## Acceptance Criteria
|
|
|
|
- [ ] LLM server running on 1050
|
|
- [ ] HTTP/gRPC endpoint exposed
|
|
- [ ] Family agent model loaded
|
|
- [ ] Function-calling support working
|
|
- [ ] Systemd/docker service configured
|
|
- [ ] Auto-restart on failure
|
|
|
|
## Technical Details
|
|
|
|
Server setup:
|
|
- Use llama.cpp or Ollama (lightweight)
|
|
- Systemd service for auto-start
|
|
- Docker option for isolation
|
|
- Lower concurrency (1-2 requests)
|
|
- Optimized for latency
|
|
|
|
## Dependencies
|
|
|
|
- TICKET-020 (family agent model selection)
|
|
- TICKET-004 (architecture)
|
|
|
|
## Related Files
|
|
|
|
- `home-voice-agent/llm-servers/1050/` (to be created)
|
|
|
|
## Notes
|
|
|
|
Optimized for always-on family agent. Lower resource usage than 4080 server.
|