mpjlu

SpeculativeDecodingPapers

📰 Must-read papers and blogs on Speculative Decoding ⚡️

NeMo-Guardrails

NeMo Guardrails is an open-source toolkit for easily adding programmable guardrails to LLM-based conversational systems.

SpecDec

Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)

onediff

OneDiff: An out-of-the-box acceleration library for diffusion models.

xFasterTransformer

awesome-model-quantization

A list of papers, docs, codes about model quantization. This repo is aimed to provide the info for model quantization research, we are continuously improving the project. Welcome to PR the works (papers, repositories) that are missed by the repo.

ColossalAI

Making large AI models cheaper, faster and more accessible

dolly

Databricks’ Dolly, a large language model trained on the Databricks Machine Learning Platform

stanford_alpaca

Code and documentation to train Stanford's Alpaca models, and generate the data.

flops-counter.pytorch

Flops counter for convolutional networks in pytorch framework

stablediffusion

High-Resolution Image Synthesis with Latent Diffusion Models

use_vim_as_ide

use vim as IDE

zw0610.github.io

transferlearning

Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习

bert4keras

keras implement of transformers for humans

bort

Repository for the paper "Optimal Subarchitecture Extraction for BERT"

tensorflow-lifetime-value

Predict customer lifetime value using AutoML Tables, or ML Engine with a TensorFlow neural network and the Lifetimes Python library.

blocksparse

Efficient GPU kernels for block-sparse matrix multiplication and convolution

CVPR2024-Papers-with-Code

CVPR 2024 论文和开源项目合集

nni

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

MegEngine

MegEngine 是一个快速、可拓展、易于使用且支持自动求导的深度学习框架

jittor

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

multi-model-server

Multi Model Server is a tool for serving neural net models for inference

moderngpu

Patterns and behaviors for GPU computing

mshadow

Matrix Shadow:Lightweight CPU/GPU Matrix and Tensor Template Library in C++/CUDA for (Deep) Machine Learning

Deep-Learning-Papers-Reading-Roadmap

Deep Learning papers reading roadmap for anyone who are eager to learn this amazing tech!

tensorflow_practice

tensorflow实战练习，包括强化学习、推荐系统、nlp等

netron

Visualizer for neural network, deep learning and machine learning models

Detectron

FAIR's research platform for object detection research, implementing popular algorithms like Mask R-CNN and RetinaNet.

cupy

NumPy & SciPy for GPU