lmdeploy is an open-source LLM inference tool published on GitHub by InternLM. The repository has collected 8.1k stars and 784 forks; the latest push was in October 2026. Related topics: codellama, cuda-kernels and deepspeed.
“LMDeploy is a toolkit for compressing, deploying, and serving LLMs.”
— InternLM, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 8,108 |
| Forks | 784 |
| Language | Python |
| License | Apache-2.0 |
| Last updated | |
| Owner | InternLM |
| Website | lmdeploy.readthedocs.io/en/latest |
| Repository | InternLM/lmdeploy |
Tags
codellamacuda-kernelsdeepspeedfastertransformerinternlmllamallama2llama3
Repository facts from the GitHub public API, refreshed October 18, 2026. The quoted tagline is written by the project owner; the summary above is generated from public facts.