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)"
☆26Updated 2 months ago
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:
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆86Updated 6 months ago
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆61Updated 10 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆102Updated 6 months ago
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆88Updated 10 months ago
- [ICML 2024] Unveiling and Harnessing Hidden Attention Sinks: Enhancing Large Language Models without Training through Attention Calibrati…☆46Updated last year
- ☆45Updated 2 months ago
- [ICML 2025] Official implementation of the paper "SkipGPT: Dynamic Layer Pruning Reinvented with Token Awareness and Module Decoupling". …☆17Updated last month
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆47Updated last year
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆150Updated 5 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆60Updated 2 months ago
- The official implementation of "LightTransfer: Your Long-Context LLM is Secretly a Hybrid Model with Effortless Adaptation"☆22Updated 8 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆68Updated 5 months ago
- ☆29Updated 6 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆196Updated 3 weeks ago
- 🚀 LLaMA-MoE v2: Exploring Sparsity of LLaMA from Perspective of Mixture-of-Experts with Post-Training☆89Updated last year
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆52Updated last year
- ☆124Updated 6 months ago
- [ICLR 2025🔥] D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models☆25Updated 5 months ago
- ☆23Updated last year
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆67Updated last year
- LongProc: Benchmarking Long-Context Language Models on Long Procedural Generation☆33Updated 2 months ago
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆113Updated last year
- ☆15Updated last year
- ☆49Updated last year
- ☆140Updated 3 months ago
- dParallel: Learnable Parallel Decoding for dLLMs☆50Updated 2 months ago
- [NeurIPS 2025] Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains☆64Updated 4 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆67Updated 8 months ago
- [ICML'24 Oral] APT: Adaptive Pruning and Tuning Pretrained Language Models for Efficient Training and Inference☆46Updated last year
- ☆41Updated 9 months ago