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)"
☆20Updated 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☆47Updated last year
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆67Updated 8 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆41Updated last year
- Quantized Side Tuning: Fast and Memory-Efficient Tuning of Quantized Large Language Models☆49Updated last year
- [ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration☆58Updated 9 months ago
- [ICLR 2025] Dynamic Mixture of Experts: An Auto-Tuning Approach for Efficient Transformer Models☆145Updated 4 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆59Updated last month
- The code for "AttentionPredictor: Temporal Pattern Matters for Efficient LLM Inference", Qingyue Yang, Jie Wang, Xing Li, Zhihai Wang, Ch…☆23Updated 4 months ago
- ☆15Updated last year
- The Official Implementation of Ada-KV [NeurIPS 2025]☆114Updated 2 months ago
- This is the official Python version of CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Act…☆17Updated last year
- ☆29Updated 6 months ago
- ☆23Updated last year
- CoT-Valve: Length-Compressible Chain-of-Thought Tuning☆87Updated 9 months ago
- An Efficient LLM Fine-Tuning Factory Optimized for MoE PEFT☆127Updated 8 months ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆83Updated 8 months ago
- [ICML'25] Our study systematically investigates massive values in LLMs' attention mechanisms. First, we observe massive values are concen…☆82Updated 5 months ago
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generation☆33Updated 6 months ago
- [EMNLP 2025] TokenSkip: Controllable Chain-of-Thought Compression in LLMs☆189Updated 5 months ago
- ☆49Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆80Updated last year
- DuoDecoding: Hardware-aware Heterogeneous Speculative Decoding with Dynamic Multi-Sequence Drafting☆17Updated 8 months ago
- Official implementation of the ICLR paper "Streamlining Redundant Layers to Compress Large Language Models"☆33Updated 6 months ago
- ☆20Updated 8 months ago
- [ACL 2025] Squeezed Attention: Accelerating Long Prompt LLM Inference☆54Updated last year
- Inference Code for Paper "Harder Tasks Need More Experts: Dynamic Routing in MoE Models"☆66Updated last year
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆72Updated last year
- Official implementation for Yuan & Liu & Zhong et al., KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark o…☆86Updated 9 months ago
- D^2-MoE: Delta Decompression for MoE-based LLMs Compression☆70Updated 8 months ago
- ☆45Updated 2 months ago