pengwu22

open-interpreter

A natural language interface for computers

Mooncake

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Quest

[ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference

llm.c

LLM training in simple, raw C/CUDA

JetStream

JetStream is a throughput and memory optimized engine for LLM inference on XLA devices, starting with TPUs (and GPUs in future -- PRs welcome).

gemma_pytorch

The official PyTorch implementation of Google's Gemma models

DeepSeek-Coder

DeepSeek Coder: Let the Code Write Itself

basic-pitch

A lightweight yet powerful audio-to-MIDI converter with pitch bend detection

photoprism

AI-Powered Photos App for the Decentralized Web 🌈💎✨

codellama

Inference code for CodeLlama models

BladeDISC

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

nccl

Optimized primitives for collective multi-GPU communication

audiocraft

Audiocraft is a library for audio processing and generation with deep learning. It features the state-of-the-art EnCodec audio compressor / tokenizer, along with MusicGen, a simple and controllable music generation LM with textual and melodic conditioning.

bitsandbytes

Accessible large language models via k-bit quantization for PyTorch.

llama.cpp

LLM inference in C/C++

vllm

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

FastChat

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

stable-diffusion-webui

Stable Diffusion web UI

ControlNet

Let us control diffusion models!

lora

Using Low-rank adaptation to quickly fine-tune diffusion models.

opennurbs

OpenNURBS libraries allow anyone to read and write the 3DM file format without the need for Rhino.

evals

Evals is a framework for evaluating LLMs and LLM systems, and an open-source registry of benchmarks.

FlexiGen

Running large language models on a single GPU for throughput-oriented scenarios.

byteir

A model compilation solution for various hardware

sheetsage

Transcribe music into lead sheets!

triton

Development repository for the Triton language and compiler

llama_index

LlamaIndex is a data framework for your LLM applications

ng-video-lecture

DeepSpeed-MII

MII makes low-latency and high-throughput inference possible, powered by DeepSpeed.

google-research

Google Research