Pinned Repositories
china_gre_query
Query all available seats of GRE in China. 查询中国的所有GRE考位信息。
Comfy-WaveSpeed
[WIP] The all in one inference optimization solution for ComfyUl, universal, flexible, and fast.
fzf-preview.vim
fzf :heart: preview
multiterm.vim
Toggle and Switch Between Multiple Floating Terminals in NeoVim or Vim
ParaAttention
[WIP] Context parallel attention that works with torch.compile
piflux
(WIP) Parallel inference for black-forest-labs' FLUX model.
pytorch-intel-mps
A fork of PyTorch that supports the use of MPS backend on Intel Mac without GPU card.
quantum-attention
(WIP) A Flash-Attention 3 counterpart that achieves peak performance on both Ampere and Hopper GPUs
stable-fast
Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
stable-fast-colab
Colab demo of stable-fast, an acceleration framework for diffusers
chengzeyi's Repositories
chengzeyi/stable-fast
Best inference performance optimization framework for HuggingFace Diffusers on NVIDIA GPUs.
chengzeyi/ParaAttention
[WIP] Context parallel attention that works with torch.compile
chengzeyi/fzf-preview.vim
fzf :heart: preview
chengzeyi/pytorch-intel-mps
A fork of PyTorch that supports the use of MPS backend on Intel Mac without GPU card.
chengzeyi/piflux
(WIP) Parallel inference for black-forest-labs' FLUX model.
chengzeyi/multiterm.vim
Toggle and Switch Between Multiple Floating Terminals in NeoVim or Vim
chengzeyi/quantum-attention
(WIP) A Flash-Attention 3 counterpart that achieves peak performance on both Ampere and Hopper GPUs
chengzeyi/china_gre_query
Query all available seats of GRE in China. 查询中国的所有GRE考位信息。
chengzeyi/stable-fast-colab
Colab demo of stable-fast, an acceleration framework for diffusers
chengzeyi/ComfyUI_stable_fast
chengzeyi/.vim_runtime
Yet a highly customized universal vim/neovim configuration.
chengzeyi/AdaptiveFloat4
A novel high-precision 4bit quantization format
chengzeyi/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.
chengzeyi/stable-diffusion-webui-stable-fast
This the AUTOMATIC1111 WebUI extension for stable-fast: A lightweight performance optimization framework for StableDiffusion
chengzeyi/vicuna-7b-delta-v0
chengzeyi/vicuna-7b-delta-v1.1
chengzeyi/.tmux_runtime
A tmux configuration
chengzeyi/champ
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
chengzeyi/codeinterpreter-api
Open source implementation of the ChatGPT Code Interpreter 👾
chengzeyi/cutlass
CUDA Templates for Linear Algebra Subroutines
chengzeyi/diffusers
🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.
chengzeyi/docker-pull-py
chengzeyi/hydrangea-vim
Hydrangea theme for Vim.
chengzeyi/LaMa-Eraser-iOS
An iOS image processing app written in SwiftUI which uses a LaMa ML model to perform image inpainting
chengzeyi/markdown-cv
a simple template to write your CV in a readable markdown file and use CSS to publish/print it.
chengzeyi/mlc-llava
Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.
chengzeyi/modded-nanogpt-rwkv
RWKV-7: Surpassing GPT
chengzeyi/Real-Time-Latent-Consistency-Model
chengzeyi/vllm
A high-throughput and memory-efficient inference and serving engine for LLMs
chengzeyi/xDiT
xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) on multi-GPU Clusters