Service-aware KV-cache compression for bandwidth-efficient disaggregated LLM serving.
☆34Nov 16, 2026Updated this week
Alternatives and similar repositories for KVServe
Users that are interested in KVServe are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- HIP version of dietGPU for the ROCm platform, featuring a GPU implementation of a fast generalized ANS (asymmetric numeral system) entrop…☆11Apr 17, 2025Updated last year
- ☆25Updated this week
- RL-AFEC: Adaptive Forward Error Correction for Real-time Video Communication Based on Reinforcement Learning☆21Oct 28, 2026Updated 2 weeks ago
- ☆25Nov 5, 2026Updated last week
- ☆10Apr 5, 2025Updated last year
- 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.
- SOSflow : Scalable Observation System for Scientific Workflows☆12Mar 9, 2020Updated 6 years ago
- GPULZ: Optimizing LZSS Lossless Compression for Multi-byte Data on Modern GPUs☆16Apr 18, 2025Updated last year
- DeepSZ: A Novel Framework to Compress Deep Neural Networks by Using Error-Bounded Lossy Compression☆12Oct 7, 2020Updated 6 years ago
- ☆15Jun 26, 2024Updated 2 years ago
- ☆19Sep 27, 2026Updated last month
- ☆38Nov 28, 2024Updated last year
- A library to abstract between different lossless and lossy compressors☆43Nov 5, 2026Updated last week
- COCCL: Compression and precision co-aware collective communication library☆40Updated this week
- This is the public repo for DREAM accepted to ICS 2025.☆12Dec 28, 2025Updated 10 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.
- BlitzScale Router - Distributed LLM Inference Router (Rust)☆18May 25, 2026Updated 5 months ago
- Taming the transient while reconfiguring BGP (SIGCOMM'23)☆10Dec 5, 2023Updated 2 years ago
- Record and replay for cellular network emulation☆34May 6, 2025Updated last year
- ☆21May 11, 2026Updated 6 months ago
- HDF5 Cache VOL connector for caching data on fast storage layers and moving data asynchronously to the parallel file system to hide I/O o…☆22Feb 10, 2026Updated 9 months ago
- An artificial matrix generator in C☆13Feb 16, 2023Updated 3 years ago
- a library to characterize the data and check the compression results of lossy compressors☆20Aug 31, 2025Updated last year
- DynaFlow: Transparent and Flexible Intra-Device Parallelism via Programmable Operator Scheduling [MLSys'26]☆14May 21, 2026Updated 5 months ago
- ☆10Sep 12, 2024Updated 2 years ago
- 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.
- Occamy is a preemptive buffer management for on-chip shared-memory switches☆13Feb 28, 2026Updated 8 months ago
- An LLM inference engine, written in C++☆20Mar 30, 2026Updated 7 months ago
- A local inspector for your agents, with a native macOS app☆21Oct 31, 2026Updated 2 weeks ago
- A drawer module for some programming language.☆11Mar 5, 2023Updated 3 years ago
- Virtual Decoupled Cores: Composable Programming Framework and Runtime for Async GPUs☆27Nov 10, 2026Updated last week
- 一个 Obsidian 插件,用于在 Obsidian 笔记和 Wolai 我来数据库之间进行双向同步。支持富文本格式、多种块类型,并提供智能的同步状态管理。☆12Jun 9, 2025Updated last year
- [ICML'26] RaBitQCache: Rotated Binary Quantization for KVCache in Long Context LLM Inference☆16Sep 14, 2026Updated 2 months ago
- ☆10Sep 3, 2017Updated 9 years ago
- Intel AMX matrix multiplication experiments☆13Jan 24, 2024Updated 2 years ago
- 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.
- Stable and Quantitative Control of Policy Entropy in RL Post-Training☆18Nov 2, 2026Updated 2 weeks ago
- ☆15Apr 11, 2024Updated 2 years ago
- [MIRROR] See gitlab.com/ocudu/ocudu for contributions☆28Updated this week
- Google DeepMind: Mixture of Depths Unofficial Implementation.☆12May 29, 2024Updated 2 years ago
- MG-WFBP: Merging Gradients Wisely for Efficient Communication in Distributed Deep Learning☆12Apr 26, 2021Updated 5 years ago
- ☆10Nov 4, 2019Updated 7 years ago
- Code for reproducing experiments performed for Accoridon☆13Jun 11, 2021Updated 5 years ago
Are these results useful?