apache/tvm-ffi
Open ABI and FFI for Machine Learning Systems
This project helps machine learning system developers build and distribute custom kernel libraries or extend existing ML frameworks like PyTorch or JAX. It provides a stable way for different programming languages and ML frameworks to exchange data and call functions with minimal overhead, allowing for a single distribution package to support multiple environments. The end user is an ML systems engineer or library developer creating high-performance components.
361 stars.
Use this if you are developing custom high-performance machine learning operations or extending ML frameworks and need consistent, efficient interoperability across different languages and runtimes.
Not ideal if you are an application-level ML practitioner who only uses existing ML models or frameworks without needing to develop custom low-level components.
Stars
361
Forks
64
Language
C++
License
Apache-2.0
Category
Last pushed
Mar 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/apache/tvm-ffi"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
apache/tvm
Open Machine Learning Compiler Framework
uxlfoundation/oneDNN
oneAPI Deep Neural Network Library (oneDNN)
Tencent/ncnn
ncnn is a high-performance neural network inference framework optimized for the mobile platform
OpenMined/TenSEAL
A library for doing homomorphic encryption operations on tensors
iree-org/iree-turbine
IREE's PyTorch Frontend, based on Torch Dynamo.