CASE-Lab-UMD / Router-Tuning-Mixture-of-DepthsLinks
The open-source Mixture of Depths code and the official implementation of the paper "Router-Tuning: A Simple and Effective Approach for Enabling Dynamic Depth in Transformers. (EMNLP 2025)"
☆16Updated last month
Alternatives and similar repositories for Router-Tuning-Mixture-of-Depths
Users that are interested in Router-Tuning-Mixture-of-Depths are comparing it to the libraries listed below
Sorting:
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆45Updated last year
- The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Ch…☆18Updated 2 months ago
- ☆15Updated 10 months ago
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆78Updated 11 months ago
- ☆28Updated 4 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆65Updated 5 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆75Updated 6 months ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆53Updated 10 months ago
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆34Updated 3 months ago
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆27Updated 11 months ago
- ☆45Updated 10 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆101Updated last year
- ☆59Updated 2 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆55Updated 7 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆49Updated 2 months ago
- Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation☆22Updated 4 months ago
- [EMNLP 2024] Quantize LLM to extremely low-bit, and finetune the quantized LLMs☆14Updated last year
- ☆119Updated 3 months ago
- An unofficial implementation of "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆36Updated last year
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆65Updated 6 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆45Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆95Updated last week
- Implementation for the paper: CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference☆25Updated 6 months ago
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆18Updated 9 months ago
- ☆25Updated last month
- ☆43Updated 5 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆80Updated 3 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆133Updated 2 months ago
- Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆37Updated 7 months ago