Learnings and programs related to CUDA

🕷️ An undetectable, powerful, flexible, high-performance Python library that makes Web Scraping easy again!

A minimal GPU design in Verilog to learn how GPUs work from the ground up

TTS with kokoro and onnx runtime

An AI-Powered Speech Processing Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Enhancement, Separation, and Target Speaker Extraction, etc.

A sound cloning tool with a web interface, using your voice or any sound to record audio / 一个带web界面的声音克隆工具，使用你的音色或任意声音来录制音频

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

📚 Freely available programming books

DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism (SVS & TTS); AAAI 2022; Official code

A Pytorch Implementation of Finite Scalar Quantization

SoftVC VITS Singing Voice Conversion

GLM-4-Voice | 端到端中英语音对话模型

first base model for full-duplex conversational audio

[ICLR 2025] SOTA discrete acoustic codec models with 40/75 tokens per second for audio language modeling

Train your own small bitnet model

Official PyTorch implementation of the paper: Flow Matching in Latent Space

TorchCFM: a Conditional Flow Matching library

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

LLM inference in C/C++

Transformer related optimization, including BERT, GPT

Get up and running with Llama 3.3, DeepSeek-R1, Phi-4, Gemma 2, and other large language models.

Collection of AWESOME vision-language models for vision tasks

Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities。

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Official inference framework for 1-bit LLMs

Python programs, usually short, of considerable difficulty, to perfect particular skills.

Inference code for the paper "Spirit-LM Interleaved Spoken and Written Language Model".

A series of math-specific large language models of our Qwen2 series.