wangcx18/llm-vscode-inference-server

An endpoint server for efficiently serving quantized open-source LLMs for code.

40
/ 100
Emerging

This project provides an alternative server for the 'llm-vscode' extension, enabling developers to run open-source code completion models locally. It takes a quantized language model file as input and serves it as an endpoint, allowing the VSCode extension to provide code suggestions and completions directly on your machine. This is ideal for software developers who want to self-host code-generating AI for their programming tasks.

No commits in the last 6 months.

Use this if you are a software developer who wants to run an open-source, quantized code Large Language Model (LLM) locally within VSCode for code completion and generation, reducing reliance on cloud services.

Not ideal if you are not a developer or if you prefer to use cloud-hosted code completion services without managing local model serving.

software-development code-completion developer-tools local-AI-inference programming
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 16 / 25

How are scores calculated?

Stars

58

Forks

10

Language

Python

License

Apache-2.0

Last pushed

Oct 15, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/wangcx18/llm-vscode-inference-server"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.