shi510

shi510's Stars

• astral-sh/uv

  An extremely fast Python package and project manager, written in Rust.

  Language:Rust25k722

• apple/ml-4m

  4M: Massively Multimodal Masked Modeling

  Language:Python1.6k94

• yorukot/superfile

  Pretty fancy and modern terminal file manager

  Language:Go5.9k128

• mit-han-lab/smoothquant

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

  Language:Python1.2k144

• mit-han-lab/qserve

  QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving

  Language:Python42622

• philipturner/metal-flash-attention

  FlashAttention (Metal Port)

  Language:Swift38119

• tspeterkim/flash-attention-minimal

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

  Language:Cuda60154

• apple/ml-ferret

  Language:Python8.4k495

• ml-explore/mlx

  MLX: An array framework for Apple silicon

  Language:C++17k982

• johnBuffer/VerletSFML-Multithread

  Multithreaded deterministic minimalist Verlet solver

  Language:C++44360

• safevideo/autollm

  Ship RAG based LLM web apps in seconds.

  Language:Python97594

• NVIDIA/TensorRT-LLM

  TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT-LLM also contains components to create Python and C++ runtimes that execute those TensorRT engines.

  Language:C++8.5k970

• microsoft/SoM

  Set-of-Mark Prompting for GPT-4V and LMMs

  Language:Python1.2k91

• OpenInterpreter/open-interpreter

  A natural language interface for computers

  Language:Python54.7k4.8k

• nuta/operating-system-in-1000-lines

  Writing an OS in 1,000 lines.

  Language:C18817

• apple/ml-fastvit

  This repository contains the official implementation of the research paper, "FastViT: A Fast Hybrid Vision Transformer using Structural Reparameterization" ICCV 2023

  Language:Python1.8k103

• logseq/logseq

  A privacy-first, open-source platform for knowledge management and collaboration. Download link: http://github.com/logseq/logseq/releases. roadmap: http://trello.com/b/8txSM12G/roadmap

  Language:Clojure32.7k1.9k

• sger/RustBooks

  List of Rust books

  4.5k297

• karpathy/llama2.c

  Inference Llama 2 in one file of pure C

  Language:C17.4k2.1k

• Nutlope/aicommits

  A CLI that writes your git commit messages for you with AI

  Language:TypeScript7.9k379

• joonspk-research/generative_agents

  Generative Agents: Interactive Simulacra of Human Behavior

  17.3k2.2k

• riffusion/riffusion-hobby

  Stable diffusion for real-time music generation

  Language:Python3.4k388

• roboflow/inference

  A fast, easy-to-use, production-ready inference server for computer vision supporting deployment of many popular model architectures and fine-tuned models.

  Language:Python1.3k123

• facebookresearch/encodec

  State-of-the-art deep learning based audio codec supporting both mono 24 kHz audio and stereo 48 kHz audio.

  Language:Python3.5k305

• huggingface/candle

  Minimalist ML framework for Rust

  Language:Rust15.7k943

• Janspiry/Palette-Image-to-Image-Diffusion-Models

  Unofficial implementation of Palette: Image-to-Image Diffusion Models by Pytorch

  Language:Python1.5k203

• pytorch/PiPPy

  Pipeline Parallelism for PyTorch

  Language:Python72586

• jupyterlab/jupyter-ai

  A generative AI extension for JupyterLab

  Language:Python3.2k324

• meta-llama/llama-recipes

  Scripts for fine-tuning Meta Llama with composable FSDP & PEFT methods to cover single/multi-node GPUs. Supports default & custom datasets for applications such as summarization and Q&A. Supporting a number of candid inference solutions such as HF TGI, VLLM for local or cloud deployment. Demo apps to showcase Meta Llama for WhatsApp & Messenger.

  Language:Jupyter Notebook14.6k2.1k

• langchain-ai/langchain

  🦜🔗 Build context-aware reasoning applications

  Language:Jupyter Notebook94.2k15.2k