astramind-ai / Mixture-of-depthsLinks
Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"
☆176Updated last year
Alternatives and similar repositories for Mixture-of-depths
Users that are interested in Mixture-of-depths are comparing it to the libraries listed below
Sorting:
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆113Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆218Updated 8 months ago
- [NeurIPS 24 Spotlight] MaskLLM: Learnable Semi-structured Sparsity for Large Language Models☆183Updated last year
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆77Updated last year
- ☆235Updated last year
- Explorations into some recent techniques surrounding speculative decoding☆299Updated last year
- Parameter-Efficient Sparsity Crafting From Dense to Mixture-of-Experts for Instruction Tuning on General Tasks (EMNLP'24)☆147Updated last year
- ☆85Updated 2 months ago
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆103Updated 7 months ago
- ☆302Updated 6 months ago
- Implementation of the paper: "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆113Updated this week
- ☆204Updated last year
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆157Updated 9 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆249Updated 10 months ago
- A family of compressed models obtained via pruning and knowledge distillation☆364Updated 2 months ago
- [NeurIPS 2024] Official Repository of The Mamba in the Llama: Distilling and Accelerating Hybrid Models☆236Updated 3 months ago
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆74Updated last year
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆88Updated 10 months ago
- ☆158Updated 11 months ago
- ☆129Updated 7 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Updated 11 months ago
- ☆273Updated 2 years ago
- [ICML 2024] Official Implementation of SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks☆39Updated 11 months ago
- The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".☆188Updated 2 months ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆105Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆113Updated 10 months ago
- ☆128Updated 2 years ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- The official repo for "LLoCo: Learning Long Contexts Offline"☆118Updated last year
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆106Updated last year