haiduo / JakiroLinks
This repository is the official implementation of "Jakiro: Boosting Speculative Decoding with Decoupled Multi-Head via MoE"
☆28Updated 4 months ago
Alternatives and similar repositories for Jakiro
Users that are interested in Jakiro are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆117Updated 5 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆128Updated 10 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆142Updated 4 months ago
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆44Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- 16-fold memory access reduction with nearly no loss☆105Updated 6 months ago
- ☆282Updated 2 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- ☆129Updated 4 months ago
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆196Updated 4 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆105Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆143Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆326Updated last week
- The official implementation of the paper "Towards Efficient Mixture of Experts: A Holistic Study of Compression Techniques (TMLR)".☆76Updated 6 months ago
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆146Updated 2 months ago
- ☆119Updated 4 months ago
- Multi-Candidate Speculative Decoding☆36Updated last year
- Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models☆137Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆49Updated 11 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆202Updated 7 months ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆172Updated last year
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆241Updated last month
- Efficient Mixture of Experts for LLM Paper List☆131Updated last week
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆339Updated 2 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆101Updated last year
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆314Updated 5 months ago