Starred repositories
Fork of xorg/fdo edid-decode with patches applied. The "default" branch is the latest rebased and patched branch I've built.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
VITS: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech
Easily train a good VC model with voice data <= 10 mins!
A throughput-oriented high-performance serving framework for LLMs
Overcoming the IOTLB Wall for Multi-100-Gbps Linux-based Networking
An LLM-powered knowledge curation system that researches a topic and generates a full-length report with citations.
Disaggregated serving system for Large Language Models (LLMs).
Fast and memory-efficient exact attention
A Datacenter Scale Distributed Inference Serving Framework
SGLang is a fast serving framework for large language models and vision language models.
The official GitHub page for the survey paper "A Survey of Large Language Models".
A low-latency & high-throughput serving engine for LLMs
Core Engine of Singing Voice Conversion & Singing Voice Clone
CoMoSVC: One-Step Consistency Model Based Singing Voice Conversion & Singing Voice Clone
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
《动手学深度学习》：面向中文读者、能运行、可讨论。中英文版被70多个国家的500多所大学用于教学。
Port of OpenAI's Whisper model in C/C++
Suno AI's Bark model in C/C++ for fast text-to-speech generation