CASE-Lab-UMD / Unified-MoE-CompressionLinks
The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
☆71Updated 3 months ago
Alternatives and similar repositories for Unified-MoE-Compression
Users that are interested in Unified-MoE-Compression are comparing it to the libraries listed below
Sorting:
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆85Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆39Updated last year
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆38Updated 10 months ago
- ☆52Updated 6 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆113Updated last month
- ☆130Updated 4 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆28Updated 4 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆71Updated 8 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆46Updated 8 months ago
- ☆104Updated 2 weeks ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆37Updated 4 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆123Updated 4 months ago
- ☆37Updated 9 months ago
- [ICML24] Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆84Updated 7 months ago
- ☆30Updated last month
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆79Updated 3 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆92Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆39Updated 2 months ago
- [ICLR 2024] Jaiswal, A., Gan, Z., Du, X., Zhang, B., Wang, Z., & Yang, Y. Compressing llms: The truth is rarely pure and never simple.☆24Updated 2 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆163Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated last year
- ☆114Updated 3 weeks ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆34Updated this week
- 16-fold memory access reduction with nearly no loss☆99Updated 3 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆47Updated 7 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆79Updated 5 months ago
- ☆42Updated 7 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆69Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆61Updated 2 months ago