Pure Rust port of eSpeak NG text-to-speech

FlyDSL is the Python front‑end of the project: Flexible LaYout DSL.

Beautiful, Modern & Opinionated Linux

A lightweight triton-based General Matrix Multiplication (GEMM) library.

Transformer related optimization, including BERT, GPT

CUDA 8-bit Tensor Core Matrix Multiplication based on m16n16k16 WMMA API

FlashRNN - Fast RNN Kernels with I/O Awareness

On-Target and Off-Target Scoring Algorithms for CRISPR gRNAs

List of software/websites/databases/other stuff for genome engineering

Haste: a fast, simple, and open RNN library

Official repository of the xLSTM.

100 days of building GPU kernels!

A bevy plugin adding edge detection post-processing effect

Hifiasm: a haplotype-resolved assembler for accurate Hifi reads

fork of dorado that supports S/BLOW5

A versatile pairwise aligner for genomic and spliced nucleotide sequences

High throughput tool for tall and wide multiple sequence alignment.

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

A collection of random, useful scripts

Environment scattering tools and shaders/materials that prioritize visual fidelity/artistic freedom, a declarative API and modularity.

FP64 equivalent GEMM by the Ozaki scheme with Int8 Tensor Cores

A binary encoder/decoder for Rust

A Client/Server game networking plugin using QUIC, for the Bevy game engine.

A little mesh raycasting plugin for Bevy

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…

Tool for demultiplexing Nanopore barcode sequence data

Lightning fast C++/CUDA neural network framework

Flash Attention in ~100 lines of CUDA (forward pass only)