pymc-labs/transpailer
LLM-based, self-correcting transpiler. Supports JAX, PyTorch, Rust, PyMC, Stan.
This project helps researchers and machine learning engineers significantly speed up their computational models. It takes models written in probabilistic programming languages like PyMC or Stan, or deep learning frameworks like JAX or PyTorch, and automatically converts them into highly optimized Rust code or other frameworks. The output is a faster, numerically validated version of your original model, ideal for anyone working with computationally intensive simulations or neural network inference.
Use this if you need to optimize the performance of your existing computational models or neural networks, especially when working with probabilistic programming or deep learning frameworks, and want to leverage Rust's speed or seamlessly move between JAX and PyTorch.
Not ideal if your models are simple and already performant enough for your needs, or if you require full manual control over every line of the transpiled code.
Stars
10
Forks
1
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 17, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pymc-labs/transpailer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Higher-rated alternatives
twiecki/transpailer
LLM-based, self-correcting transpiler, supports Jax, PyToch, Rust, PyMC, Stan
pymc-labs/transalchemy
LLM-based, self-correcting transpiler. Supports JAX, PyTorch, Rust, PyMC, Stan.
kyegomez/JaxTransformer
This repository demonstrates how to build a Decoder-Only Transformer with Multi-Query Attention in JAX.
Arneunalarming861/Laminae
Bridge raw large language models to production-ready AI with a lightweight Rust layer enabling...