方飞虎's starred repositories
ThunderKittens
Tile primitives for speedy kernels
PowerInfer
High-speed Large Language Model Serving on PCs with Consumer-grade GPUs
chromebook-linux-audio
Script to enable audio support on many Chrome devices
clash-for-linux-backup
基于Clash Core 制作的Clash For Linux备份仓库 A Clash For Linux Backup Warehouse Based on Clash Core
text-generation-inference
Large Language Model Text Generation Inference
Megatron-LM
Ongoing research training transformer models at scale
lean-side-bussiness
精益副业:程序员如何优雅地做副业
MixtralKit
A toolkit for inference and evaluation of 'mixtral-8x7b-32kseqlen' from Mistral AI
AnimateAnyone
Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation
magic-animate
[CVPR 2024] MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
whisper-jax
JAX implementation of OpenAI's Whisper model for up to 70x speed-up on TPU.
ControlNet
Let us control diffusion models!
AnimeInbet
Code and data for ICCV23 work "Deep Geometrized Cartoon Line Inbetweening"
chromebrew
Package manager for Chrome OS
tensorrt_plugin_generator
A simple tool that can generate TensorRT plugin code quickly.
opt_einsum
⚡️Optimizing einsum functions in NumPy, Tensorflow, Dask, and more with contraction order optimization.
DirectML
DirectML is a high-performance, hardware-accelerated DirectX 12 library for machine learning. DirectML provides GPU acceleration for common machine learning tasks across a broad range of supported hardware and drivers, including all DirectX 12-capable GPUs from vendors such as AMD, Intel, NVIDIA, and Qualcomm.
just-the-docs
A modern, high customizable, responsive Jekyll theme for documentation with built-in search.