CanyonWind

segmoe

MoE-LLaVA

Mixture-of-Experts for Large Vision-Language Models

web-llm

High-performance In-browser LLM Inference Engine

ml-engineering

Machine Learning Engineering Open Book

llama-moe

⛷️ LLaMA-MoE: Building Mixture-of-Experts from LLaMA with Continual Pre-training (EMNLP 2024)

mistral-inference

Official inference library for Mistral models

moe_attention

Official repository for the paper "SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention"

oneflow

OneFlow is a deep learning framework designed to be user-friendly, scalable and efficient.

dilated-attention-pytorch

(Unofficial) Implementation of dilated attention from "LongNet: Scaling Transformers to 1,000,000,000 Tokens" (https://arxiv.org/abs/2307.02486)

dilated-self-attention

Implementation of the dilated self attention as described in "LongNet: Scaling Transformers to 1,000,000,000 Tokens"

TorchIntegral

Integral Neural Networks in PyTorch

Segment-and-Track-Anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

tomesd

Speed up Stable Diffusion with this one simple trick!

web-stable-diffusion

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

tuning_playbook

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

nni

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

FasterTransformer

Transformer related optimization, including BERT, GPT

MegCC

MegCC是一个运行时超轻量，高效，移植简单的深度学习模型编译器

dmls-book

Summaries and resources for Designing Machine Learning Systems book (Chip Huyen, O'Reilly 2022)

TransformerEngine

A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit floating point (FP8) precision on Hopper and Ada GPUs, to provide better performance with lower memory utilization in both training and inference.

GenNAS

Generic Neural Architecture Search via Regression (NeurIPS'21 Spotlight)

xformers

Hackable and optimized Transformers building blocks, supporting a composable construction.

FLASHQuad_pytorch

FLASHQuad_pytorch

diffusion_distiller

🚀 PyTorch Implementation of "Progressive Distillation for Fast Sampling of Diffusion Models(v-diffusion)"

FLASH-pytorch

Implementation of the Transformer variant proposed in "Transformer Quality in Linear Time"

TensorRT

PyTorch/TorchScript/FX compiler for NVIDIA GPUs using TensorRT

guided-inpainting

Towards Unified Keyframe Propagation Models

einops

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

flash-attention

Fast and memory-efficient exact attention