[ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
☆117May 24, 2024Updated last year
Alternatives and similar repositories for Expert_Sparsity
Users that are interested in Expert_Sparsity are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆23Nov 11, 2025Updated 5 months ago
- Code for this paper "HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts via HyperNetwork"☆33Nov 29, 2023Updated 2 years ago
- A block pruning framework for LLMs.☆28May 17, 2025Updated 10 months ago
- ☆29May 24, 2024Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆145Sep 20, 2024Updated last year
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- ThinK: Thinner Key Cache by Query-Driven Pruning☆29Feb 11, 2025Updated last year
- ☆23Nov 26, 2024Updated last year
- A simple and effective LLM pruning approach.☆860Aug 9, 2024Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆91Feb 28, 2026Updated last month
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆105Jun 20, 2025Updated 9 months ago
- [ICML‘25] Official code for paper "Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training an…☆13Apr 17, 2025Updated 11 months ago
- [Pattern Recognition 2024] Semantic-Aware Frame-Event Fusion based Pattern Recognition via Large Vision-Language Models, Dong Li, Jiandon…☆18Jan 18, 2025Updated last year
- A full codebase for replicating the results of Nougat from downloading arXiv dataset to the final evaluation. It also contains a few fixe…☆11Dec 11, 2023Updated 2 years ago
- Official implementation of Add-SD: Rational Generation without Manual Reference.☆28Aug 19, 2024Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- ☆52May 13, 2024Updated last year
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆126May 7, 2024Updated last year
- Official implementation for LaCo (EMNLP 2024 Findings)☆21Oct 3, 2024Updated last year
- Extract a single expert from a Mixture Of Experts model using slerp interpolation.☆19May 26, 2024Updated last year
- [TMLR'24] This repository includes the official implementation our paper "FedConv: Enhancing Convolutional Neural Networks for Handling D…☆25Apr 30, 2024Updated last year
- Initialization using Update Approximation is a Silver Bullet for Extremely Efficient Low-Rank Fine-Tuning☆52Oct 17, 2025Updated 5 months ago
- ☆49Jan 18, 2024Updated 2 years ago
- Make reasoning models scalable☆49May 31, 2025Updated 10 months ago
- The official implementation for Collaborative Word-based Pre-trained Item Representation for Transferable Recommendation.☆25Jan 30, 2024Updated 2 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Official implementation of the ICLR paper "Streamlining Redundant Layers to Compress Large Language Models"☆41May 1, 2025Updated 11 months ago
- PyTorch implementation of "Learning from Students: Online Contrastive Distillation Network for General Continual Learning" (IJCAI 2022)☆11Dec 29, 2022Updated 3 years ago
- Project for SNARE benchmark☆11Jun 5, 2024Updated last year
- [ICML 2025] MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design☆27Jul 4, 2025Updated 9 months ago
- ☆30Jul 22, 2024Updated last year
- The official implementation of the NeurIPS 2022 paper Q-ViT.☆105May 22, 2023Updated 2 years ago
- ☆145Jul 21, 2024Updated last year
- [ICLR 2023] 'Revisiting Pruning At Initialization Through The Lens of Ramanujan Graph" by Duc Hoang, Shiwei Liu, Radu Marculescu, Atlas W…☆14Aug 4, 2023Updated 2 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆45Feb 28, 2026Updated last month
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 2024Updated last year
- ☆17Oct 12, 2023Updated 2 years ago
- The open-source materials for paper "Sparsing Law: Towards Large Language Models with Greater Activation Sparsity".☆30Nov 12, 2024Updated last year
- Official Code for paper "Towards Efficient and Effective Unlearning of Large Language Models for Recommendation" (Frontiers of Computer S…☆38Jul 19, 2024Updated last year
- Backtracing: Retrieving the Cause of the Query, EACL 2024 Long Paper, Findings.☆92Jul 21, 2024Updated last year
- The official implementation of HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization☆18Mar 7, 2025Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆98Nov 25, 2024Updated last year