antgroup / OmniKVLinks
Dynamic Context Selection for Efficient Long-Context LLMs
☆40Updated 4 months ago
Alternatives and similar repositories for OmniKV
Users that are interested in OmniKV are comparing it to the libraries listed below
Sorting:
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated 2 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆40Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆45Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆127Updated 9 months ago
- ☆279Updated 2 months ago
- 16-fold memory access reduction with nearly no loss☆105Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆168Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 11 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
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆32Updated 7 months ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆110Updated 6 months ago
- ☆142Updated 7 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆141Updated 4 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆60Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated last month
- ☆119Updated 3 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- [ICLR‘24 Spotlight] Code for the paper "Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy"☆93Updated 3 months ago
- ☆78Updated 5 months ago
- Implementation for FP8/INT8 Rollout for RL training without performence drop.☆207Updated last week
- Odysseus: Playground of LLM Sequence Parallelism☆77Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆333Updated 2 months ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆189Updated 3 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆92Updated 2 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆152Updated last month
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆63Updated 2 months ago
- Official implementation of ICML 2024 paper "ExCP: Extreme LLM Checkpoint Compression via Weight-Momentum Joint Shrinking".☆48Updated last year
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆78Updated 10 months ago
- ☆33Updated 7 months ago