Search Results - RepositoryStats

801

4.4k

apache-2.0

132

Neural Network Distiller by Intel AI Lab: a Python package for neural network compression research. https://intellabs.github.io/distiller

onnx pruning pytorch early-exit group-lasso distillation quantization truncated-svd regularization jupyter-notebook pruning-structures network-compression deep-neural-networks automl-for-compression

This repository has been archived (exclude archived)

Created 2018-04-24

643 commits to master branch, last one about a year ago

16

230

other

6

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

llm early-exit layer-drop optimization transformers speculative-decoding

Created 2024-02-26

26 commits to main branch, last one 24 days ago

1

29

mit

1

A curated list of early exiting (LLM, CV, NLP, etc)

cnn gpt llm nlp survey early-exit paper-list awesome-list early-exiting computer-vision

Created 2023-08-01

8 commits to main branch, last one 3 months ago