JianchaoTan

JARVIS

JARVIS, a system to connect LLMs with ML community. Paper: https://arxiv.org/pdf/2303.17580.pdf

LLMsPracticalGuide

A curated list of practical guide resources of LLMs (LLMs Tree, Examples, Papers)

nebuly

The user analytics platform for LLMs

dynet

DyNet: The Dynamic Neural Network Toolkit

alpa

Training and serving large-scale neural networks with auto parallelization.

ddsp

DDSP: Differentiable Digital Signal Processing

llm-awq

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

yoha

A practical hand tracking engine.

Graphormer

Graphormer is a general-purpose deep learning backbone for molecular modeling.

lion-pytorch

🦁 Lion, new optimizer discovered by Google Brain using genetic algorithms that is purportedly better than Adam(w), in Pytorch

xatlas

Mesh parameterization / UV unwrapping library

tomesd

Speed up Stable Diffusion with this one simple trick!

smoothquant

[ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

AutoGL

An autoML framework & toolkit for machine learning on graphs.

blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

BladeDISC

BladeDISC is an end-to-end DynamIc Shape Compiler project for machine learning workloads.

TinyNeuralNetwork

TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.

VIMER

视觉预训练基础模型仓库

ByteTransformer

optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052

PERSIA

High performance distributed framework for training deep learning recommendation models based on PyTorch.

AI-Software-Startups

A Survey of AI startups

Sophia

Effortless plugin and play Optimizer to cut model training costs by 50%. New optimizer that is 2x faster than Adam on LLMs.

nn-Meter

A DNN inference latency prediction toolkit for accurately modeling and predicting the latency on diverse edge devices.

Dynamic-Vision-Transformer

Accelerating T2t-ViT by 1.6-3.6x.

torch-int

This repository contains integer operators on GPUs for PyTorch.

LLaMA-8bit-LoRA

Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.

Merak

PINAT

[AAAI '23] PINAT: A Permutation INvariance Augmented Transformer for NAS Predictor

cxhull

Convex hull in arbitrary dimension

SeCNN

SeCNN: A Semantic CNN Parser for Code Comment Generation