tonyw

tonyw's Repositories

• tonyw/chats

  10

• tonyw/ChatTTS

  A generative speech model for daily dialogue.

• tonyw/Chinese-LLaMA-Alpaca

  中文LLaMA&Alpaca大语言模型+本地CPU/GPU部署 (Chinese LLaMA & Alpaca LLMs)

  Language:Python00

• tonyw/co

  An elegant and efficient C++ basic library for Linux, Windows and Mac.

  Language:C++10

• tonyw/CosyVoice

  Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

• tonyw/cuda-samples

  Samples for CUDA Developers which demonstrates features in CUDA Toolkit

  Language:C00

• tonyw/cutlass

  CUDA Templates for Linear Algebra Subroutines

  Language:C++00

• tonyw/EAGLE

  Official Implementation of EAGLE

  Language:Python00

• tonyw/gpuassembler

  10

• tonyw/Kubernetes

  00

• tonyw/learn-cuda

  A complete CUDA tutorial ranging from first GPU programs to advanced asynchronous methods

  Language:Cuda00

• tonyw/lobe-chat

  🤯 Lobe Chat - an open-source, modern-design AI chat framework. Supports Multi AI Providers( OpenAI / Claude 3 / Gemini / Ollama / Azure / DeepSeek), Knowledge Base (file upload / knowledge management / RAG ), Multi-Modals (Vision/TTS) and plugin system. One-click FREE deployment of your private ChatGPT/ Claude application.

• tonyw/macOS-QQ-WeChat-API

  用于 macOS 使用 QQ、微信获取用户好友、获取聊天记录、打开与指定好友的聊天窗口、对指定好友发送任意消息的 API 接口

  Language:Python00

• tonyw/my_docker_images

  Language:Shell20

• tonyw/ragflow

  RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

• tonyw/RedPajama-Data

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

  Language:Python00

• tonyw/so-vits-svc

  SoftVC VITS Singing Voice Conversion

  Language:Python00

• tonyw/TigerBot

  TigerBot: A multi-language multi-task LLM

  Language:Python00

• tonyw/TLLM_QMM

  TLLM_QMM strips the implementation of quantized kernels of Nvidia's TensorRT-LLM, removing NVInfer dependency and exposes ease of use Pytorch module. We modified the dequantation and weight preprocessing to align with popular quantization alogirthms such as AWQ and GPTQ, and combine them with new FP8 quantization.

  Language:C++00

• tonyw/tuning_playbook

  A playbook for systematically maximizing the performance of deep learning models.

  00

• tonyw/vllm

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

  Language:Python00

• tonyw/WeChatExtension-ForMac

  Mac微信功能拓展/微信插件/微信小助手(A plugin for Mac WeChat)

  Language:Objective-C00