Beast code in Giters

Chenxia Han's starred repositories

ThunderKittens

Tile primitives for speedy kernels

Language:CudaMIT109300

LLaMA-VID

Official Implementation for LLaMA-VID: An Image is Worth 2 Tokens in Large Language Models

Language:PythonApache-2.059800

lightllm

LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalability, and high-speed performance.

Language:PythonApache-2.0189600

flash-attention

Fast and memory-efficient exact attention

Language:PythonBSD-3-Clause1121700

gpt-fast

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

Language:PythonBSD-3-Clause520500

PySceneDetect

:movie_camera: Python and OpenCV-based scene cut/transition detection program & library.

Language:PythonNOASSERTION285700

Medusa

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

Language:Jupyter NotebookApache-2.0191600

hugo-theme-ladder

A fast, clean Hugo theme | 一个简单而优雅的 hugo 主题

Language:HTMLMIT14600

MovieChat

[CVPR 2024] 🎬💭 chat with over 10K frames of video!

Language:PythonBSD-3-Clause41200

composer

Supercharge Your Model Training

Language:PythonApache-2.0502800

GPTCache

Semantic cache for LLMs. Fully integrated with LangChain and llama_index.

Language:PythonMIT651200

MiniGPT-4

Open-sourced codes for MiniGPT-4 and MiniGPT-v2 (https://minigpt-4.github.io, https://minigpt-v2.github.io/)

Language:PythonBSD-3-Clause2500000

RedPajama-Data

The RedPajama-Data repository contains code for preparing large datasets for training large language models.

Language:PythonApache-2.0439100

stable-diffusion-videos

Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

Language:PythonApache-2.0426300

the-algorithm

Source code for Twitter's Recommendation Algorithm

Language:ScalaAGPL-3.06151200

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Language:Jupyter NotebookApache-2.04459000

PiPPy

Pipeline Parallelism for PyTorch

Language:PythonBSD-3-Clause63500

typst

A new markup-based typesetting system that is powerful and easy to learn.

Language:RustApache-2.02889400

the-algorithm-ml

Source code for Twitter's Recommendation Algorithm

Language:PythonAGPL-3.0992100

llama_index

LlamaIndex is a data framework for your LLM applications

Language:PythonMIT3190000

ultralytics

NEW - YOLOv8 🚀 in PyTorch > ONNX > OpenVINO > CoreML > TFLite

Language:PythonAGPL-3.02395200

chatgpt-retrieval-plugin

The ChatGPT Retrieval Plugin lets you easily find personal or work documents by asking questions in natural language.

Language:PythonMIT2089400

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

Language:PythonApache-2.02894700

paul-graham-gpt

AI search & chat for all of Paul Graham’s essays.

Language:TypeScriptMIT261700

xorbits

Scalable Python DS & ML, in an API compatible & lightning fast way.

Language:PythonApache-2.0102300

poetry

Python packaging and dependency management made easy

Language:PythonMIT2973800

timely-dataflow

A modular implementation of timely dataflow in Rust

Language:RustMIT319600

instill-core

🔮 Instill Core is an open-source no-/low-code data, model and pipeline orchestration platform, providing a full-stack solution for AI-first applications

Language:MakefileNOASSERTION191000

tensorstore

Library for reading and writing large multi-dimensional arrays.

Language:C++NOASSERTION130000

uncertainty-toolbox

Uncertainty Toolbox: a Python toolbox for predictive uncertainty quantification, calibration, metrics, and visualization

Language:PythonMIT173200