LMDeploy
Local LLM RunnersToolkit for compressing and serving large language models
Replaces OpenAI API, Hugging Face Inference Endpoints
Self-hosted apps by InternLM
2 self-hosted projects maintained by InternLM on GitHub — combined community: 15,046 GitHub stars.
Portfolio at a glance
The 2 projects span 2 categories: local llm runners and search engines. LMDeploy is the flagship at 8,104 stars — Toolkit for compressing and serving large language models. 1 of 2 are written primarily in Python. The oldest dates from 2023 and the newest from 2024. 2 publish a Docker deployment path.
| Projects | 2 |
|---|---|
| Combined stars | 15,046 |
| Hosted on | GitHub |
| Languages | Python (1), JavaScript (1) |
| Licenses | Apache-2.0 (2) |
| Setup difficulty | Medium (1), Hard (1) |
| Min. RAM range | 2,048–16,384 MB |
| First releases | 2023–2024 |