LLM KV cache compression made easy
☆1,196Aug 18, 2026Updated last week
Alternatives and similar repositories for kvpress
Users that are interested in kvpress are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆737Aug 16, 2026Updated 2 weeks ago
- [NeurIPS'25 Oral] Query-agnostic KV cache eviction: 3–4× reduction in memory and 2× decrease in latency (Qwen3/2.5, Gemma3, LLaMA3)☆224Feb 11, 2026Updated 6 months ago
- The Official Implementation of Ada-KV [NeurIPS 2025]☆139Nov 26, 2025Updated 9 months ago
- ☆332Jul 10, 2025Updated last year
- FlashInfer: Kernel Library for LLM Serving☆6,290Updated this week
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆431Nov 20, 2025Updated 9 months ago
- [NeurIPS'24 Spotlight, ICLR'25, ICML'25] To speed up Long-context LLMs' inference, approximate and dynamic sparse calculate the attention…☆1,226Apr 8, 2026Updated 4 months ago
- Awesome-LLM-KV-Cache: A curated list of 📙Awesome LLM KV Cache Papers with Codes.☆465Jun 17, 2026Updated 2 months ago
- [ICML 2025 Spotlight] ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference☆313May 1, 2025Updated last year
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆404Jul 10, 2025Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆854Mar 6, 2025Updated last year
- This repository serves as a comprehensive survey of LLM development, featuring numerous research papers along with their corresponding co…☆352Jul 16, 2026Updated last month
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆532Aug 1, 2024Updated 2 years ago
- Accurate and fast KV cache compression with a gating mechanism☆29Jul 27, 2026Updated last month
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆539Feb 10, 2025Updated last year
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆256Dec 16, 2024Updated last year
- LMCache: Supercharge Your LLM with the Fastest KV Cache Layer☆11,572Updated this week
- KV cache compression for high-throughput LLM inference☆160Feb 5, 2025Updated last year
- 🚀 Efficient implementations for emerging model architectures☆5,665Updated this week
- Official Implementation for [ICLR26] DefensiveKV: Taming the Fragility of KV Cache Eviction in LLM Inference☆58Mar 28, 2026Updated 5 months ago
- Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).☆2,516Feb 20, 2026Updated 6 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,131Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,220Updated this week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆7,306Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,136Sep 4, 2024Updated last year
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆283Jul 6, 2025Updated last year
- Distributed Compiler and Optimized Parallel Kernels☆1,529Aug 12, 2026Updated 2 weeks ago
- A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on H…☆3,511Updated this week
- Accelerating MoE with IO and Tile-aware Optimizations☆752Updated this week
- Efficient LLM Inference over Long Sequences☆392Jun 25, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,438Updated this week
- Perplexity GPU Kernels☆604Nov 7, 2025Updated 9 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- Awesome LLM compression research papers and tools.☆1,865Updated this week
- ☆40Mar 17, 2025Updated last year
- ☆47Nov 25, 2024Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆171Oct 13, 2025Updated 10 months ago
- Tile primitives for speedy kernels☆3,659Updated this week
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆153Aug 9, 2024Updated 2 years ago
- Unified KV Cache Compression Methods for Auto-Regressive Models☆1,375Aug 13, 2026Updated 2 weeks ago