open-lm-engine/coda-kernels

DeepGEMM: clean and efficient BLAS kernel library on GPU

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

An agent harness that compiles a model into one provably-correct, self-retargeting CUDA megakernel and self-tunes it past cuBLAS at batch-1 LLM decode, paper: https://arxiv.org/abs/2606.09682

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance with lower memory utilization in both training and inference.

A Quirky Assortment of CuTe Kernels

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Winner 🏆 (Agent-only) MLSys 2026 - FlashInfer AI Kernel Generation Contest for the DeepSeek Sparse Attention (DSA) track with an average speedup of 34.93x

Tokamax: A GPU and TPU kernel library.

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.