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
- TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆98Updated last week
- ☆70Updated last week
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆85Updated 10 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆59Updated 5 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆61Updated this week
- Code accompanying the paper "Massive Activations in Large Language Models"☆150Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆42Updated last month
- ☆36Updated 6 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆33Updated 8 months ago
- Homepage for ProLong (Princeton long-context language models) and paper "How to Train Long-Context Language Models (Effectively)"☆166Updated 2 weeks ago
- [ICML 2024 Oral] This project is the official implementation of our Accurate LoRA-Finetuning Quantization of LLMs via Information Retenti…☆63Updated 11 months ago
- XAttention: Block Sparse Attention with Antidiagonal Scoring☆102Updated this week
- ☆49Updated 10 months ago
- ☆71Updated this week
- ☆127Updated 8 months ago
- ☆17Updated 3 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆55Updated last month
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆34Updated 7 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆34Updated 9 months ago
- ☆116Updated last month
- Code for "Everybody Prune Now: Structured Pruning of LLMs with only Forward Passes"☆27Updated 11 months ago
- Efficient triton implementation of Native Sparse Attention.☆116Updated this week
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆57Updated 5 months ago
- The source code of "Merging Experts into One: Improving Computational Efficiency of Mixture of Experts (EMNLP 2023)":☆36Updated 11 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆35Updated last month
- ☆38Updated 4 months ago
- Official implementation of "DoRA: Weight-Decomposed Low-Rank Adaptation"☆123Updated 10 months ago
- 🔥 A minimal training framework for scaling FLA models☆82Updated this week
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆52Updated last month
- ☆83Updated last week