π° Must-read papers on KV Cache Compression (constantly updating π€).
β674Feb 24, 2026Updated 3 weeks ago
Alternatives and similar repositories for Awesome-KV-Cache-Compression
Users that are interested in Awesome-KV-Cache-Compression are comparing it to the libraries listed below
Sorting:
- Awesome-LLM-KV-Cache: A curated list of πAwesome LLM KV Cache Papers with Codes.β418Mar 3, 2025Updated last year
- LLM KV cache compression made easyβ971Mar 13, 2026Updated last week
- The Official Implementation of Ada-KV [NeurIPS 2025]β128Nov 26, 2025Updated 3 months ago
- β306Jul 10, 2025Updated 8 months ago
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Headsβ531Feb 10, 2025Updated last year
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attentionβ¦β1,198Mar 9, 2026Updated last week
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cacheβ359Nov 20, 2025Updated 4 months ago
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding coβ¦β293Dec 5, 2025Updated 3 months ago
- Pytorch implementation of our paper accepted by ICML 2024 -- CaM: Cache Merging for Memory-efficient LLMs Inferenceβ48Jun 19, 2024Updated last year
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.β506Aug 1, 2024Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inferenceβ377Jul 10, 2025Updated 8 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projectionβ155Feb 20, 2025Updated last year
- π° Must-read papers and blogs on Speculative Decoding β‘οΈβ1,145Mar 9, 2026Updated last week
- Awesome LLM compression research papers and tools.β1,789Feb 23, 2026Updated 3 weeks ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inferenceβ286May 1, 2025Updated 10 months ago
- Unified KV Cache Compression Methods for Auto-Regressive Modelsβ1,311Jan 4, 2025Updated last year
- KV Cache Compression, But What Must We Give in Return? A Comprehensive Benchmark of Long Context Capable Approaches. EMNLP Findings 2024β89Feb 27, 2025Updated last year
- β36Mar 17, 2025Updated last year
- π° Must-read papers and blogs on LLM based Long Context Modeling π₯β1,938Feb 27, 2026Updated 3 weeks ago
- πA curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.πβ5,062Updated this week
- A curated list for Efficient Large Language Modelsβ1,967Jun 17, 2025Updated 9 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Seβ¦β818Mar 6, 2025Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decodingβ144Dec 4, 2024Updated last year
- Since the emergence of chatGPT in 2022, the acceleration of Large Language Model has become increasingly important. Here is a list of papβ¦β281Mar 6, 2025Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLMβ180Jul 12, 2024Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inferenceβ164Oct 13, 2025Updated 5 months ago
- ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction (NIPS'24)β52Dec 17, 2024Updated last year
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top ofβ¦β149Aug 9, 2024Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Servingβ336Jul 2, 2024Updated last year
- β52May 13, 2024Updated last year
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decodingβ277Aug 31, 2024Updated last year
- [EMNLP 2024 Findingsπ₯] Official implementation of ": LOOK-M: Look-Once Optimization in KV Cache for Efficient Multimodal Long-Context Inβ¦β104Nov 9, 2024Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoringβ273Jul 6, 2025Updated 8 months ago
- (ACL 2025 oral) SCOPE: Optimizing KV Cache Compression in Long-context Generationβ34May 28, 2025Updated 9 months ago
- β85Apr 18, 2025Updated 11 months ago
- β65Apr 26, 2025Updated 10 months ago
- FlashInfer: Kernel Library for LLM Servingβ5,145Mar 15, 2026Updated last week
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generationβ251Dec 16, 2024Updated last year
- [ACL 2024 (Oral)] A Prospector of Long-Dependency Data for Large Language Modelsβ60Jul 23, 2024Updated last year