LLMkvsys / rethink-kv-compressionLinks
☆17Updated 5 months ago
Alternatives and similar repositories for rethink-kv-compression
Users that are interested in rethink-kv-compression are comparing it to the libraries listed below
Sorting:
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆47Updated 3 weeks ago
- SQUEEZED ATTENTION: Accelerating Long Prompt LLM Inference☆52Updated 9 months ago
- Beyond KV Caching: Shared Attention for Efficient LLMs☆19Updated last year
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inference☆42Updated last year
- The official implementation of paper: SimLayerKV: A Simple Framework for Layer-Level KV Cache Reduction.☆48Updated 10 months ago
- Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton☆31Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆104Updated 5 months ago
- AdaSkip: Adaptive Sublayer Skipping for Accelerating Long-Context LLM Inference☆15Updated 7 months ago
- ☆41Updated 3 months ago
- LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification☆63Updated last month
- ☆14Updated last year
- ☆15Updated 5 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆90Updated 2 months ago
- ☆33Updated 6 months ago
- This repo contains the source code for: Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs☆39Updated last year
- Source code for the paper "LongGenBench: Long-context Generation Benchmark"☆23Updated 10 months ago
- Official Repo for SparseLLM: Global Pruning of LLMs (NeurIPS 2024)☆64Updated 5 months ago
- ☆18Updated 8 months ago
- Transformers components but in Triton☆34Updated 3 months ago
- ☆26Updated 3 months ago
- Source code of paper ''KVSharer: Efficient Inference via Layer-Wise Dissimilar KV Cache Sharing''☆28Updated 10 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [arXiv '25]☆49Updated last month
- ☆117Updated 2 months ago
- ☆56Updated 8 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆43Updated last month
- Official Implementation of FastKV: KV Cache Compression for Fast Long-Context Processing with Token-Selective Propagation☆22Updated 3 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆114Updated 2 months ago
- PipeRAG: Fast Retrieval-Augmented Generation via Algorithm-System Co-design (KDD 2025)☆24Updated last year
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆59Updated last year