// Run models locally
tvmv0.27.0.post1
Open Machine Learning Compiler Framework
Open source Maintained For developers
IN ONE PARAGRAPH
tvm is open Machine Learning Compiler Framework.
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:
npm install tvmjs - 3Try it on a small example before wiring it into a project.
02Alternatives & comparison
Compare side by side → executorch On-device AI across mobile, embedded and edge for PyTorch ★ 5.1k MNN MNN: A blazing-fast, lightweight inference engine battle-tested by Alibaba, powering high-performance on-device LLMs and Edge AI. ★ 16k server The Triton Inference Server provides an optimized cloud and edge inferencing solution. ★ 11k mediapipe Cross-platform, customizable ML solutions for live and streaming media. ★ 37k ncnn ncnn is a high-performance neural network inference framework optimized for the mobile platform ★ 24k
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
- v0.27.0.post1 2026-09-29
- v0.27.0 2026-09-25
- v0.26.0 2026-08-11
- v0.25.0.post1 2026-06-24
- v0.25.0 2026-06-19
For AI agents
- Interfaces：SDK
- Machine-readable record：/api/v1/software/tvm.json · llms.txt
- Added 2026-10-10 · updated 2026-10-22