pan-x-c / EE-LLMLinks
EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).
☆74Updated last year
Alternatives and similar repositories for EE-LLM
Users that are interested in EE-LLM are comparing it to the libraries listed below
Sorting:
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆176Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆142Updated last year
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆177Updated last year
- ☆158Updated 11 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆65Updated last year
- ☆64Updated last year
- ☆303Updated 7 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆116Updated 3 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆155Updated 3 weeks ago
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆88Updated 10 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆155Updated 11 months ago
- ☆131Updated 8 months ago
- Explorations into some recent techniques surrounding speculative decoding☆299Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆220Updated 8 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆160Updated 4 months ago
- ☆39Updated last year
- 16-fold memory access reduction with nearly no loss☆110Updated 10 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆40Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆114Updated 10 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
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆106Updated last year
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆222Updated last year
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆105Updated last year
- [ACL 2024] Not All Experts are Equal: Efficient Expert Pruning and Skipping for Mixture-of-Experts Large Language Models☆114Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆88Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆49Updated last year
- KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. EMNLP Findings 2024☆88Updated 11 months ago
- The evaluation framework for training-free sparse attention in LLMs☆117Updated 2 weeks ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆147Updated last month