Interact with your documents using the power of GPT, 100% privately, no data leaks

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

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

Universal LLM Deployment Engine with ML Compilation

利用AI大模型，一键生成高清短视频 Generate short videos with one click using AI LLM.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

Fast and memory-efficient exact attention

ChatGLM3 series: Open Bilingual Chat LLMs | 开源双语对话语言模型

Letta (fka MemGPT) is a framework for creating stateful LLM services.

An open-source tool-augmented conversational language model from Fudan University

This project aim to reproduce Sora (Open AI T2V model), we wish the open source community contribute to this project.

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Build high-quality LLM apps - from prototyping, testing to production deployment and monitoring.

A PyTorch Extension: Tools for easy mixed precision and distributed training in Pytorch

SkyPilot: Run AI and batch jobs on any infra (Kubernetes or 12+ clouds). Get unified execution, cost savings, and high GPU availability via a simple interface.

DeepSeek Coder: Let the Code Write Itself

[ICLR 2024] Efficient Streaming Language Models with Attention Sinks

SGLang is a fast serving framework for large language models and vision language models.

Tiled Diffusion and VAE optimize, licensed under CC BY-NC-SA 4.0

SwinIR: Image Restoration Using Swin Transformer (official repository)

Code examples and resources for DBRX, a large language model developed by Databricks

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

MambaOut: Do We Really Need Mamba for Vision?

S-LoRA: Serving Thousands of Concurrent LoRA Adapters

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

Enforce the output format (JSON Schema, Regex etc) of a language model

A family of open-sourced Mixture-of-Experts (MoE) Large Language Models

Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.