CASE-Lab-UMD / Unified-MoE-Compression
The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".
☆66Updated last month
Alternatives and similar repositories for Unified-MoE-Compression:
Users that are interested in Unified-MoE-Compression are comparing it to the libraries listed below
- [ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆81Updated 10 months ago
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆81Updated 5 months ago
- ☆122Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆63Updated 6 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆36Updated 2 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆87Updated 11 months ago
- ☆36Updated 7 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆37Updated 10 months ago
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆45Updated 6 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆46Updated 5 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆35Updated 10 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆58Updated 10 months ago
- ☆50Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆102Updated last month
- 16-fold memory access reduction with nearly no loss☆90Updated 3 weeks ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆94Updated last week
- ☆37Updated 6 months ago
- Official Pytorch Implementation of "Outlier Weighed Layerwise Sparsity (OWL): A Missing Secret Sauce for Pruning LLMs to High Sparsity"☆64Updated 9 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆51Updated 9 months ago
- ☆76Updated last week
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆36Updated 8 months ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 6 months ago
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆72Updated last month
- Code for studying the super weight in LLM☆98Updated 4 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆158Updated 10 months ago
- SliM-LLM: Salience-Driven Mixed-Precision Quantization for Large Language Models☆29Updated 8 months ago
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆64Updated last year
- ☆237Updated 11 months ago
- 🔥 A minimal training framework for scaling FLA models☆107Updated last week