Ther-nullptr/Awesome-Transformer-Accleration
Paper list for accleration of transformers
This is a curated list of research papers and implementations focused on making large language models (LLMs) and other transformer-based AI models run faster and more efficiently. It compiles methods like quantization and pruning, which reduce the computational resources needed, along with system and hardware improvements. The ideal user is an AI/ML engineer or researcher working on deploying or optimizing these complex models for practical applications.
No commits in the last 6 months.
Use this if you are a machine learning engineer or researcher looking for state-of-the-art techniques to optimize the performance, speed, or memory footprint of transformer models like Vision Transformers, BERT, and GPT for real-world deployment.
Not ideal if you are looking for an off-the-shelf, ready-to-use software library to simply apply acceleration without diving into academic research or technical implementations.
Stars
14
Forks
2
Language
—
License
—
Category
Last pushed
Jul 01, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Ther-nullptr/Awesome-Transformer-Accleration"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
oscarknagg/few-shot
Repository for few-shot learning machine learning projects
jakesnell/prototypical-networks
Code for the NeurIPS 2017 Paper "Prototypical Networks for Few-shot Learning"
harveyslash/Facial-Similarity-with-Siamese-Networks-in-Pytorch
Implementing Siamese networks with a contrastive loss for similarity learning
google-research/meta-dataset
A dataset of datasets for learning to learn from few examples
akshaysharma096/Siamese-Networks
Few Shot Learning by Siamese Networks, using Keras.