// Run models locally
flashinferv0.7.2
FlashInfer: Kernel Library for LLM Serving
Open source Maintained For developers
IN ONE PARAGRAPH
flashinfer is flashInfer: Kernel Library for LLM Serving.
Good for: Developers and teams who want to run models locally.
01How to start
- 1Read the official quick-start (link above).
- 2Install from the official package registry:
pip install flashinfer-python - 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → TensorRT-LLM TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way. ★ 15k gpustack A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances. ★ 5.9k sglang SGLang is a high-performance serving framework for large language models and multimodal models. ★ 38k llm-d Achieve state of the art inference performance with modern accelerators on Kubernetes ★ 4.9k LMCache LMCache: Supercharge Your LLM with the Fastest KV Cache Layer ★ 12k
03Related
- ›Elements of AI · 赫尔辛基大学 / MinnaLearnMultilingual (incl. EN/ZH)
- ›AI For Everyone · DeepLearning.AI / 吴恩达English
- ›Generative AI for Everyone · DeepLearning.AI / 吴恩达English
- ›Introduction to Generative AI 学习路径 · Google Cloud SkillsEnglish
- ›Microsoft Learn: Fundamentals of Generative AI · Microsoft LearnMultilingual (incl. EN/ZH)
- All tutorials →
Versions, why it is listed, for AI to read
Recent releases
- v0.7.1 2026-10-09
- v0.7.0.post1 2026-09-29
- v0.7.0 2026-09-22
- v0.6.18.post1 2026-09-05
- v0.6.18 2026-08-29
For AI agents
- Interfaces：SDK
- Machine-readable record：/api/v1/software/flashinfer.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22