Narsil

rdev

Simple library to listen and send events to keyboard and mouse (MacOS, Windows, Linux)

alphagozero

Unofficial attempt to rebuild AlphaGo Zero

hf-chat

bindgen_cuda

esaxx-rs

Bindings to copy of SentencePiece esaxx library (fast suffix array and frequent substrings).

zandle

Testing zig comptime out for complex tensor typing thing.

serde_pyo3

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

mistral.rs

Blazingly fast LLM inference.

rcfiles

Personal files

zig_cuda_bug

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

candle-rotary

candle-selective-scan

cudarc

Safe rust wrapper around CUDA toolkit

doc-builder

The package used to build the documentation of our Hugging Face repos

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

face

Small demo to apply 3d filter in the browser with onnx js

flash-attention

Fast and memory-efficient exact attention

flashinfer

FlashInfer: Kernel Library for LLM Serving

kernels_test

kernels_test2

llama.cpp

LLM inference in C/C++

narsil.github.io

My blog from fastpages

nixpkgs

Nix Packages collection & NixOS

serde-rs.github.io

tailscale-action

Github action to connect to tailscale

tgi-nix

wavem

wd