[ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models
☆124May 24, 2024Updated 2 years ago
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:
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆88Mar 25, 2025Updated last year
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆111Jun 20, 2025Updated last year
- Code for this paper "HyperRouter: Towards Efficient Training and Inference of Sparse Mixture of Experts via HyperNetwork"☆34Nov 29, 2023Updated 2 years ago
- A block pruning framework for LLMs.☆28May 17, 2025Updated last year
- [ICML 2025] Retraining-Free Merging of Sparse MoE via Hierarchical Clustering☆24Oct 26, 2025Updated last year
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- DALI Multi Agent System Framework☆42Mar 24, 2026Updated 7 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆93Oct 2, 2026Updated last month
- ☆146Jul 21, 2024Updated 2 years ago
- Mixture-of-Basis-Experts for Compressing MoE-based LLMs☆41Dec 24, 2025Updated 10 months ago
- (ICLR 2026) Unveiling Super Experts in Mixture-of-Experts Large Language Models☆44Sep 25, 2025Updated last year
- ThinK: Thinner Key Cache by Query-Driven Pruning☆30Jun 2, 2026Updated 5 months ago
- [ICML 2025] MxMoE: Mixed-precision Quantization for MoE with Accuracy and Performance Co-Design☆33Jul 4, 2025Updated last year
- ☆29May 24, 2024Updated 2 years ago
- Efficient Mixture of Experts for LLM Paper List☆191Jun 16, 2026Updated 4 months 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.
- A simple and effective LLM pruning approach.☆880Aug 9, 2024Updated 2 years ago
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆143Sep 20, 2024Updated 2 years ago
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆51Apr 9, 2024Updated 2 years ago
- ☆12Jul 22, 2026Updated 3 months ago
- [NAACL'25 🏆 SAC Award] Official code for "Advancing MoE Efficiency: A Collaboration-Constrained Routing (C2R) Strategy for Better Expert…☆18Feb 4, 2025Updated last year
- [NeurIPS2024] "Read-ME: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design", Ruisi Cai, Yeonju Ro, Geon-Woo …☆17Dec 16, 2024Updated last year
- Co-LLM: Learning to Decode Collaboratively with Multiple Language Models☆130May 7, 2024Updated 2 years ago
- BESA is a differentiable weight pruning technique for large language models.☆17Mar 4, 2024Updated 2 years ago
- Code Repository for the NeurIPS 2024 Paper "Toward Efficient Inference for Mixture of Experts".☆19Oct 30, 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.
- Official Pytorch Implementation of Self-emerging Token Labeling☆34Mar 27, 2024Updated 2 years ago
- ☆23Nov 26, 2024Updated last year
- Sparsity as a Variance Regulator for Improved Depth Utilization in Language Models☆16May 11, 2026Updated 5 months ago
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆74Jul 30, 2024Updated 2 years ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆49Oct 2, 2026Updated last month
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆165Jul 9, 2025Updated last year
- A repository aimed at pruning DeepSeek V3, R1 and R1-zero to a usable size☆88Sep 5, 2025Updated last year
- ☆35Jan 23, 2024Updated 2 years ago
- MISO: Exploiting Multi-Instance GPU Capability on Multi-Tenant GPU Clusters☆21Apr 21, 2023Updated 3 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆10Feb 15, 2025Updated last year
- The code for "MoPE: Mixture of Prefix Experts for Zero-Shot Dialogue State Tracking"☆19Jan 25, 2025Updated last year
- Code of the paper "Efficient Object Detection in Autonomous Driving using Spiking Neural Networks: Performance, Energy Consumption Analys…☆28Dec 13, 2023Updated 2 years ago
- FuseAI Project☆601Jan 25, 2025Updated last year
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆100Nov 25, 2024Updated last year
- A Model Agnostic function to directly remove specified layers from the LLM☆11May 23, 2024Updated 2 years ago
- ☆27Oct 4, 2024Updated 2 years ago