trholding

llama2.c

Llama 2 Everywhere (L2E)

AMICA

AMICA FK20K

audiosamples

Audio Samples

buildrump.sh

Utilities for building rump kernels

cFS

The Core Flight System (cFS)

CLBlast

Tuned OpenCL BLAS

cosmopolitan

build-once run-anywhere c library

CTranslate2

Fast inference engine for Transformer models

dlprimitives

Deep Learning Primitives and Mini-Framework for OpenCL

gatsby-ecommerce-site

hypertext-editor

Hypertext HTML Document Editor

musika

Fast Infinite Waveform Music Generation

pytorch_dlprim

DLPrimitives/OpenCL out of tree backend for pytorch

spleeter

Deezer source separation library including pretrained models.

Stretch

KiCad to SVG and then back again

gemma.cpp

Gemma 2 Everywhere (G2E) WIP

ggml

Tensor library for machine learning

grok-1

Grok open release

linux

Linux kernel source tree

linux-xtensa

Linux port for xtensa architecture. None of these branches are stable.

llama.cpp

Port of Facebook's LLaMA model in C/C++

Llama2.jl

llama2.c but in Julia

llamafile

Distribute and run LLMs with a single file.

llm.c

LLM training in simple, raw C/CUDA

LLMzip

rumprun

The Rumprun unikernel and toolchain for various platforms

src-netbsd

Automatic conversion of the NetBSD src CVS module, use with care. Please submit bugs/changes via https://gnats.netbsd.org

whisper

Robust Speech Recognition via Large-Scale Weak Supervision - OpenCL Accelerated Fork (WIP)

whisper.cpp

Port of OpenAI's Whisper model in C/C++