Google Git Google Git
Sign in
apache/tvm-ffi

Open ABI and FFI for Machine Learning Systems

Mirrored from https://github.com/apache/tvm-ffi.git
Clone this repo:

Branches

Tags

More...
  1. ba02ead [Rust] Use AnyView in structural traversal callbacks (#892) by Tianqi Chen · 5 hours ago main
  2. 455bf7b [FEAT][Rust] Add object downcast_ref to Any, AnyView and managed references (#891) by Tianqi Chen · 5 hours ago
  3. 69be48a [FEAT] Enrich structural traversal errors through root type hooks (#889) by Tianqi Chen · 2 days ago
  4. 1cfa5f7 Constrain Optional's constructors for C++20 (#887) by Tom Fogal · 3 days ago
  5. e9fdc58 [FEAT][Rust] Replace rs_class placeholders with an UnsafeInit creator (#886) by Linzhang Li · 4 days ago v0.1.15-post2

TVM FFI: Open ABI and FFI for Machine Learning Systems

📚 Documentation | 🚀 Quickstart

Apache TVM FFI is an open ABI and FFI for machine learning systems. It is a minimal, framework-agnostic, yet flexible open convention with the following systems in mind:

  • Kernel libraries - ship one wheel to support multiple frameworks, Python versions, and different languages. [FlashInfer]
  • Kernel DSLs - reusable open ABI for JIT and AOT kernel exposure frameworks and runtimes. [TileLang][cuteDSL]
  • Frameworks and runtimes - a uniform extension point for ABI-compliant libraries and DSLs. [PyTorch][JAX][PaddlePaddle][NumPy/CuPy]
  • ML infrastructure - out-of-box bindings and interop across languages. [Python][C++][Rust][XGrammar]
  • Coding agents - a unified mechanism for shipping generated code in production.

Features

  • Stable, minimal C ABI designed for kernels, DSLs, and runtime extensibility.
  • Zero-copy interop across PyTorch, JAX, and CuPy using DLPack protocol.
  • Compact value and call convention covering common data types for ultra low-overhead ML applications.
  • Multi-language support out of the box: Python, C++, and Rust (with a path towards more languages).

These enable broad interoperability across frameworks, libraries, DSLs, and agents; the ability to ship one wheel for multiple frameworks and Python versions (including free-threaded Python); and consistent infrastructure across environments.

Getting Started

Install TVM-FFI with pip, uv or from source:

pip install apache-tvm-ffi
pip install torch-c-dlpack-ext  # compatibility package for torch <= 2.9

Status and Release Versioning

C ABI stability is our top priority.

Status: RFC Main features are complete and ABI stable. We recognize potential needs for evolution to ensure it works best for the machine learning systems community, and would like to work together with the community for such evolution. We plan to stay in the RFC stage for three months from the v0.1.0 release.

Releases during the RFC stage will be 0.X.Y, where bumps in X indicate C ABI-breaking changes and Y indicates other changes. We anticipate the RFC stage will last for three months, then we will start following Semantic Versioning (major.minor.patch) going forward.

Documentation

Our documentation site includes:

Get Started

Guides

Concepts

Packaging

Developer Manual