ziliangpeng

whisper

Robust Speech Recognition via Large-Scale Weak Supervision

DeepSpeed

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

ruff

An extremely fast Python linter and code formatter, written in Rust.

awesome-docker

:whale: A curated list of Docker resources and projects

vllm

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

mojo

The Mojo Programming Language

gpt-2

Code for the paper "Language Models are Unsupervised Multitask Learners"

Awesome-LLM

Awesome-LLM: a curated list of Large Language Model

mlx

MLX: An array framework for Apple silicon

triton

Development repository for the Triton language and compiler

mistral-src

Reference implementation of Mistral AI 7B v0.1 model.

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

llama-cpp-python

Python bindings for llama.cpp

cuda-samples

Samples for CUDA Developers which demonstrates features in CUDA Toolkit

mlx-examples

Examples in the MLX framework

gpt-fast

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

ROCm

AMD ROCm™ Software - GitHub Home

llm

Access large language models from the command-line

iree

A retargetable MLIR-based machine learning compiler and runtime toolkit.

minitorch

The full minitorch student suite.

awesome-language-agents

List of language agents based on paper "Cognitive Architectures for Language Agents"

Awesome-CUDA

This is a list of useful libraries and resources for CUDA development.

transformer-pytorch

Transformer implementation in PyTorch.

stablehlo

Backward compatible ML compute opset inspired by HLO/MHLO

Hands-On-GPU-Programming-with-Python-and-CUDA

Hands-On GPU Programming with Python and CUDA, published by Packt

My-ebook

ctypeslib

Generate python ctypes classes from C headers. Requires LLVM clang

llm-mistral

LLM plugin providing access to Mistral models using the Mistral API

py-metal-compute

A python library to run metal compute kernels on macOS

metal-python

Python API client for metal-api