This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm-ffi.git
The following commit(s) were added to refs/heads/main by this push:
new 9268e67 doc: Update README.md (#352)
9268e67 is described below
commit 9268e6740f968d5fdd70ced548d2534f3a27d337
Author: Junru Shao <[email protected]>
AuthorDate: Mon Dec 22 06:38:12 2025 -0800
doc: Update README.md (#352)
[[Rendered](https://github.com/junrushao/tvm-ffi/blob/636f7448a57f9fbd2a67431e9766013805abb82c/README.md)]
---
README.md | 23 +++++++++++++++++++----
1 file changed, 19 insertions(+), 4 deletions(-)
diff --git a/README.md b/README.md
index 91901a6..3fbd2cc 100644
--- a/README.md
+++ b/README.md
@@ -22,10 +22,10 @@
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.
-- **Kernel DSLs** - reusable open ABI for JIT and AOT kernel exposure
frameworks and runtimes.
-- **Frameworks and runtimes** - a uniform extension point for ABI-compliant
libraries and DSLs.
-- **ML infrastructure** - out-of-the-box bindings and interop for Python, C++,
and Rust.
+- **Kernel libraries** - ship one wheel to support multiple frameworks, Python
versions, and different languages. [[FlashInfer](https://docs.flashinfer.ai/)]
+- **Kernel DSLs** - reusable open ABI for JIT and AOT kernel exposure
frameworks and runtimes.
[[TileLang](https://tilelang.com/)][[cuteDSL](https://docs.nvidia.com/cutlass/latest/media/docs/pythonDSL/cute_dsl_general/compile_with_tvm_ffi.html)]
+- **Frameworks and runtimes** - a uniform extension point for ABI-compliant
libraries and DSLs.
[[PyTorch](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-pytorch)][[JAX](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-jax)][[NumPy/CuPy](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-numpy)]
+- **ML infrastructure** - out-of-box bindings and interop across languages.
[[Python](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-python)][[C++](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-cpp)][[Rust](https://tvm.apache.org/ffi/get_started/quickstart.html#ship-to-rust)]
- **Coding agents** - a unified mechanism for shipping generated code in
production.
## Features
@@ -37,6 +37,21 @@ yet flexible open convention with the following systems in
mind:
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:
+
+```bash
+pip install apache-tvm-ffi
+pip install torch-c-dlpack-ext # compatibility package for torch <= 2.9
+```
+
+Visit our [documentation](https://tvm.apache.org/ffi/) to learn more.
+
+- [Quick Start](https://tvm.apache.org/ffi/get_started/quickstart.html)
+- [Stable C ABI](https://tvm.apache.org/ffi/get_started/stable_c_abi.html)
+- [Python
Packaging](https://tvm.apache.org/ffi/packaging/python_packaging.html)
+
## Status and Release Versioning
**C ABI stability** is our top priority.
