C (chengzeyi)

chengzeyi

User data from Github https://github.com/chengzeyi

Company:https://wavespeed.ai/

Location:wavespeed.ai

Home Page:https://chengzeyi.github.io/markdown-cv/

GitHub:@chengzeyi

Twitter:@chengzeyi


Organizations
WaveSpeedAI

C's repositories

stable-fast

https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.

Language:PythonLicense:MITStargazers:1287Issues:16Issues:131

Comfy-WaveSpeed

https://wavespeed.ai/ [WIP] The all in one inference optimization solution for ComfyUI, universal, flexible, and fast.

Language:PythonLicense:MITStargazers:1154Issues:11Issues:128

ParaAttention

https://wavespeed.ai/ Context parallel attention that accelerates DiT model inference with dynamic caching

Language:PythonLicense:NOASSERTIONStargazers:375Issues:7Issues:26

fzf-preview.vim

fzf :heart: preview

pytorch-intel-mps

A fork of PyTorch that supports the use of MPS backend on Intel Mac without GPU card.

Language:C++License:NOASSERTIONStargazers:29Issues:1Issues:0

piflux

(WIP) Parallel inference for black-forest-labs' FLUX model.

Language:PythonLicense:NOASSERTIONStargazers:18Issues:2Issues:5

multiterm.vim

Toggle and Switch Between Multiple Floating Terminals in NeoVim or Vim

Language:Vim ScriptLicense:MITStargazers:11Issues:2Issues:2

stable-fast-colab

Colab demo of stable-fast, an acceleration framework for diffusers

Language:Jupyter NotebookStargazers:5Issues:1Issues:0

.vim_runtime

Yet a highly customized universal vim/neovim configuration.

Language:Vim ScriptLicense:MITStargazers:1Issues:3Issues:0

AdaptiveFloat4

A novel high-precision 4bit quantization format

docker-ubuntu-desktop

Docker Image for Ubuntu Desktop which support HW GPU accelerated GUI apps. you can access the Container with ssh or remote desktop, just like Cloud VM.

Language:DockerfileLicense:MITStargazers:1Issues:1Issues:0

stable-diffusion-webui-stable-fast

This the AUTOMATIC1111 WebUI extension for stable-fast: A lightweight performance optimization framework for StableDiffusion

License:MITStargazers:1Issues:3Issues:0

.tmux_runtime

A tmux configuration

Language:ShellStargazers:0Issues:3Issues:0

champ

Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

codeinterpreter-api

Open source implementation of the ChatGPT Code Interpreter 👾

Language:PythonLicense:MITStargazers:0Issues:1Issues:0

cutlass

CUDA Templates for Linear Algebra Subroutines

Language:C++License:NOASSERTIONStargazers:0Issues:0Issues:0

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonStargazers:0Issues:1Issues:0
Stargazers:0Issues:0Issues:0

flash-attention

Fast and memory-efficient exact attention

Language:PythonLicense:BSD-3-ClauseStargazers:0Issues:0Issues:0

hydrangea-vim

Hydrangea theme for Vim.

Language:Vim ScriptLicense:MITStargazers:0Issues:1Issues:0

markdown-cv

a simple template to write your CV in a readable markdown file and use CSS to publish/print it.

Language:CSSLicense:MITStargazers:0Issues:1Issues:0

mlc-llava

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

modded-nanogpt-rwkv

RWKV-7: Surpassing GPT

Language:PythonStargazers:0Issues:0Issues:0

nunchaku

SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models

Language:CudaLicense:Apache-2.0Stargazers:0Issues:0Issues:0
Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

ThunderKittens

Tile primitives for speedy kernels

License:MITStargazers:0Issues:0Issues:0

vllm

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

Language:PythonLicense:Apache-2.0Stargazers:0Issues:1Issues:0

xDiT

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters

Language:PythonLicense:Apache-2.0Stargazers:0Issues:0Issues:0