UNITES-Lab / MC-SMoE
[ICLR 2024 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"
☆74Updated 9 months ago
Alternatives and similar repositories for MC-SMoE:
Users that are interested in MC-SMoE are comparing it to the libraries listed below
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆84Updated 9 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆57Updated 4 months ago
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆27Updated 11 months ago
- [ICLR 2025] When Attention Sink Emerges in Language Models: An Empirical View (Spotlight)☆50Updated 4 months ago
- ☆115Updated 3 weeks ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆32Updated 8 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆35Updated 9 months ago
- The official implementation of the paper "Demystifying the Compression of Mixture-of-Experts Through a Unified Framework".☆60Updated 4 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆162Updated last week
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆56Updated 5 months ago
- 🔥 A minimal training framework for scaling FLA models☆75Updated this week
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆62Updated 10 months ago
- ☆17Updated 3 months ago
- ☆38Updated 3 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆34Updated 6 months ago
- ☆49Updated 10 months ago
- [NeurIPS 2024 Spotlight] EMR-Merging: Tuning-Free High-Performance Model Merging☆49Updated last week
- ☆36Updated 6 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆40Updated 2 weeks ago
- [NeurIPS2024] Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging☆51Updated 3 months ago
- ☆123Updated 7 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆33Updated 9 months ago
- Official Pytorch Implementation of Our Paper Accepted at ICLR 2024-- Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLM…☆45Updated 11 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆152Updated 8 months ago
- ☆50Updated last year
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆124Updated 10 months ago