Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

CUDA Templates for Linear Algebra Subroutines

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

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

Applied AI experiments and examples for PyTorch

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Official release of InternLM2.5 base and chat models. 1M context support

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

Development repository for the Triton language and compiler

Serving multiple LoRA finetuned LLM as one

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

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

Ongoing research training transformer models at scale

Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.

A Deep Learning based project for colorizing and restoring old images (and video!)

StyleGAN2 - Official TensorFlow Implementation

CUDA Kernel Benchmarking Library

An unidentifiable mechanism that helps you bypass GFW.

⭐ Linux / Windows / macOS 跨平台 V2Ray 客户端 | 支持 VMess / VLESS / SSR / Trojan / Trojan-Go / NaiveProxy / HTTP / HTTPS / SOCKS5 | 使用 C++ / Qt 开发 | 可拓展插件式设计 ⭐

v2ray节点、免费节点、免费v2ray节点、最新公益免费v2ray节点订阅地址、免费v2ray节点每日更新、免费ss/v2ray/trojan节点、freefq

A web GUI client of Project V which supports VMess, VLESS, SS, SSR, Trojan, Tuic and Juicity protocols. 🚀

FlashInfer: Kernel Library for LLM Serving

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Universal markup converter

A V2Ray client for Android, support Xray core and v2fly core

A GUI client for Windows, Linux and macOS, support Xray core and sing-box-core and others

Animation engine for explanatory math videos

Acode - powerful text/code editor for android

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