pymc-labs/transalchemy
LLM-based, self-correcting transpiler. Supports JAX, PyTorch, Rust, PyMC, Stan.
This tool helps data scientists, statisticians, and machine learning engineers convert their computational models between different programming languages like PyMC, Stan, JAX, PyTorch, and optimized Rust. You provide your existing model code, and it automatically generates an equivalent, validated, and often much faster version in a different language, complete with numerical checks. This is designed for practitioners who build and deploy probabilistic models or deep learning systems.
Use this if you need to migrate an existing computational model or deep learning network to a different language or framework to improve performance, integrate with other systems, or leverage specialized hardware like GPUs or Apple Silicon.
Not ideal if you are developing a new model from scratch and don't have an existing implementation to convert.
Stars
10
Forks
1
Language
Rust
License
Apache-2.0
Category
Last pushed
Mar 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/pymc-labs/transalchemy"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
twiecki/transpailer
LLM-based, self-correcting transpiler, supports Jax, PyToch, Rust, PyMC, Stan
pymc-labs/transpailer
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...