xllm is an open-source LLM inference tool published on GitHub by xLLM-AI. With 1.6k stars on GitHub, it was last updated in October 2026. Docs and downloads are linked from xllm-ai.com.
“A high-performance inference engine for LLM, VLM, DiT and REC models, optimized for diverse AI accelerators. It is hosted in OpenAtom Foundation.”
— xLLM-AI, project description on GitHub
Details
| Category | Local LLMs & Inference |
|---|---|
| GitHub stars | 1,601 |
| Forks | 313 |
| Language | C++ |
| License | Apache-2.0 |
| Last updated | |
| Owner | xLLM-AI |
| Website | xllm-ai.com |
| Repository | xLLM-AI/xllm |
Tags
deepseekglminferenceinference-enginelarge-language-modelsllm-inferenceqwen
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.