grctest/FastAPI-BitNet
View on GitHub ↗Running Microsoft's BitNet inference framework via FastAPI, Uvicorn and Docker.
40 ★13 forksPythonUpdated 1y ago
What you need to know
FastAPI + Docker REST API wrapper for llama.cpp BitNet instances, exposed to VS Code Copilot via fastapi-mcp. Lets you run and query BitNet quantized models through MCP.
Key features
- ✓FastAPI + Docker REST API for llama.cpp BitNet
- ✓VS Code Copilot integration via fastapi-mcp
- ✓BitNet quantized model serving
Best for
Running BitNet models and exposing them to VS Code Copilot
Clients: VS Code Copilot
Documentation ↗Reviewed 2026-08-11
Topics
1-bitbenchmarkingbitnetdockerfastapiinferencellmmodel-context-protocolmulti-chatperplexitypythonserver-orchestrationuvicorn
- Stars
- 40★
- Forks
- 13
- Language
- Python
- License
- MIT
- Created
- 2024-11-10
- Last push
- 2025-07-02