physicsrob/torchwright

Conveniently export torch.compile compiled products into self-contained Python files

LLM-based, self-correcting transpiler. Supports JAX, PyTorch, Rust, PyMC, Stan.

Convert Machine Learning Code Between Frameworks

A multi-framework neural network compiler lowering PyTorch, JAX, Flax, and Keras models to portable, high-performance GGML execution

Compile programs directly into transformer weights. Includes a 2D convex-hull KV cache with O(log n) inference.

PyTorch compiler that accelerates training and inference. Get built-in optimizations for performance, memory, parallelism, and easily write your own.

A place to store reusable transformer components of my own creation or found on the interwebs

TensorIR is a lightweight NVIDIA-owned MLIR compiler frontend for expressing tensor computations and lowering them to NVIDIA CUDA Tile IR.