Tiered shared KV cache storage for LLM inference. Extends GPU HBM to host memory, NVMe, and JBOF pools — enabling cross-instance prefix reuse for vLLM, Dynamo, and NIXL.
☆12Sep 30, 2026Updated last month
Alternatives and similar repositories for ContextStore
Users that are interested in ContextStore are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Provides deploy scripts and CSI for Lustre.☆14Oct 23, 2026Updated 3 weeks ago
- Model Serving Signals☆22Updated this week
- A LevelDB for implementing LSM-related papers☆11Aug 7, 2023Updated 3 years ago
- Cloud native observability for the high-speed AI networks.☆103Updated this week
- Parallel git worktrees for parallel AI agents — plus AI-generated commits.☆27Nov 5, 2026Updated 2 weeks 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.
- ☆12May 22, 2023Updated 3 years ago
- The main purpose of runtime copilot is to assist with node runtime management tasks such as configuring registries, upgrading versions, i…☆13May 16, 2023Updated 3 years ago
- ☆10Jul 6, 2023Updated 3 years ago
- An Envoy inspired, ultimate LLM-first gateway for LLM serving and downstream application developers and enterprises☆27Apr 24, 2025Updated last year
- ☆13Nov 5, 2026Updated 2 weeks ago
- ZettaStor DBS provides enterprise-level business storage solutions with high availability, high performance, easy expansion and easy main…☆75Dec 23, 2025Updated 10 months ago
- GitHub Repo for STAR: Scaling Transactions through Asymmetric Replication☆21Jun 28, 2019Updated 7 years ago
- d.run website☆18Nov 4, 2026Updated 2 weeks ago
- ☆17Nov 3, 2026Updated 2 weeks 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.
- Let CI Robot automatically execute commands for your PR/issue in your Github repository, hosting on Github Action does not require your s…☆13Oct 19, 2026Updated last month
- 中国开发者活动日程(关注点:开源、开发者、云原生)☆31Updated this week
- This project is designed to simulate GPU information, making it easier to test scenarios where a GPU is not available.☆65Jan 9, 2026Updated 10 months ago
- Operator that manages HwameiStor☆11Oct 27, 2026Updated 3 weeks ago
- 🧯 Kubernetes coverage for fault awareness and recovery, works for any LLMOps, MLOps, AI workloads.☆35Updated this week
- Various tools created for my work in NERSC ATG☆10Oct 24, 2025Updated last year
- Scripts for the Lustre File System and Robinhood Policy Engine☆11Aug 31, 2023Updated 3 years ago
- Go interface for Lustre's utility library (liblustreapi).☆11Mar 9, 2022Updated 4 years ago
- A light abstraction for common file system functions.☆16Aug 21, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- Workflow Defined Engine☆25Nov 4, 2025Updated last year
- Platform + GUI for hyperparameter optimization of recurrent neural networks (MATLAB).☆10Dec 29, 2021Updated 4 years ago
- Ansible automation to deploy a multi arch PXE Boot Server☆14Aug 9, 2025Updated last year
- C-ray — X-ray your containers. See beneath the runtime.☆23Jun 25, 2026Updated 4 months ago
- Test Orchestrator for Performance and Scalability of AI pLatforms☆18Jun 23, 2026Updated 4 months ago
- 学习笔记☆10Feb 18, 2025Updated last year
- A distributed in-memory store for temporal knowledge graphs☆10Mar 20, 2024Updated 2 years ago
- Mirror of my work branch☆11Nov 27, 2022Updated 3 years ago
- A collection of useful Go libraries to ease the development of NVIDIA Operators for GPU/NIC management.☆30Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- llm-d-batch-gateway is a standalone, backend-agnostic, OpenAI-compatible batch API and processing engine☆28Updated this week
- ☆58Updated this week
- ☆22Mar 11, 2026Updated 8 months ago
- Kubernetes controllers for fast model actuation using vLLM sleep/wake and launcher-based model swapping☆28Updated this week
- Source code for Lotus: Scalable Multi-Partition Transactions on Single-Threaded Partitioned Databases☆48Jul 31, 2022Updated 4 years ago
- LZW压缩算法的完整实现☆10Aug 14, 2014Updated 12 years ago
- An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.☆366Updated this week
Are these results useful?