A curated list of early exiting (LLM, CV, NLP, etc)
☆74Aug 21, 2024Updated 2 years ago
Alternatives and similar repositories for early-exit-papers
Users that are interested in early-exit-papers are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆83Jun 14, 2024Updated 2 years ago
- PipeEdge: Pipeline Parallelism for Large-Scale Model Inference on Heterogeneous Edge Devices☆43Jan 31, 2024Updated 2 years ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆67Sep 28, 2024Updated last year
- PyTorch implementation of the paper: Multi-Agent Collaborative Inference via DNN Decoupling: Intermediate Feature Compression and Edge Le…☆46Oct 26, 2023Updated 2 years ago
- PyTorch implementation of the SIESTA algorithm from our TMLR-2023 paper "SIESTA: Efficient Online Continual Learning with Sleep"☆13Oct 25, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- PyTorch implementation of the paper: Decomposing Vision Transformers for Collaborative Inference in Edge Devices☆18Jul 27, 2024Updated 2 years ago
- Numerical Evaluation and Implementation of paper: Workflow Optimization for paper Parallel Split Learning (IEEE INFOCOM 2024).☆24Jul 15, 2026Updated last month
- ☆14Jul 17, 2020Updated 6 years ago
- [Neurips 2021] Sparse Training via Boosting Pruning Plasticity with Neuroregeneration☆31Feb 11, 2023Updated 3 years ago
- ☆14Nov 24, 2022Updated 3 years ago
- ☆18Jun 13, 2022Updated 4 years ago
- Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals; ACL 2024☆13May 24, 2024Updated 2 years ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆21Jan 24, 2025Updated last year
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆16Oct 3, 2023Updated 2 years ago
- Python package for Dec-POMDP files in the .dpomdp format☆11Oct 28, 2022Updated 3 years ago
- Code for "Fast Sparse ConvNets" CVPR2020 submissions☆12Nov 20, 2019Updated 6 years ago
- A curated reading list of research in Adaptive Computation, Inference-Time Computation & Mixture of Experts (MoE).☆165Jan 1, 2025Updated last year
- [UbiComp 2020] Intermittent Learning: On-Device Machine Learning on Intermittently Powered System☆10May 28, 2020Updated 6 years ago
- This is the official code for UGTs.☆13Feb 8, 2023Updated 3 years ago
- ☆19Jan 5, 2020Updated 6 years ago
- ☆215Jan 17, 2024Updated 2 years ago
- [ECMLPKDD 2020] "Topological Insights into Sparse Neural Networks"☆13May 2, 2022Updated 4 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆22Jan 7, 2025Updated last year
- [ICLR2025] γ -MOD: Mixture-of-Depth Adaptation for Multimodal Large Language Models☆45Oct 28, 2025Updated 10 months ago
- This repository is established to store personal notes and annotated papers during daily research.☆200Jun 28, 2026Updated 2 months ago
- Less is More: High-value Data Selection for Visual Instruction Tuning☆20Jan 18, 2025Updated last year
- Explore, Establish, Exploit: Red Teaming Language Models from Scratch☆15Jun 21, 2023Updated 3 years ago
- ☆10Oct 5, 2023Updated 2 years ago
- Work in progress LLM framework.☆16Oct 31, 2024Updated last year
- Code for testing DCT plus Sparse (DCTpS) networks☆14Jun 15, 2021Updated 5 years ago
- ☆16Sep 6, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2024] Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity; Lu Yin*, Ajay Jaiswal*, Shiwei Liu, So…☆16Apr 21, 2025Updated last year
- ☆18Aug 24, 2026Updated 2 weeks ago
- ☆14Dec 14, 2022Updated 3 years ago
- ☆13Mar 14, 2023Updated 3 years ago
- ☆22Jul 5, 2024Updated 2 years ago
- [MobiSys 2020] Fast and Scalable In-memory Deep Multitask Learning via Neural Weight Virtualization☆15Jun 9, 2020Updated 6 years ago
- Code for the paper "Knowledge-Aware Federated Active Learning with Non-IID Data", ICCV2023☆10Sep 8, 2023Updated 2 years ago