← Latest products

An RDMA/Infiniband Distributed Cache for Fast Inference and Training

A high-performance RDMA distributed file system for fast LLM Inference and GPU Training.

Open source

47 stars · GitHubexternal site

Visit github.comexternal site

Reactions (1)

Similar products

by description similarity

  1. Cuts Long Horizon Inference Costs by 50% via external KV Cache Offload

    github.com

    OpenLake is a high performance storage engine for efficient LLM inference and GPU Training

    Hacker News22 pts

  2. Speeding up LLM inference 2x times (possibly)

    asciinema.org

    Here's a project I've been working on for the last few months.

    Hacker News419 pts

  3. UnisonDB

    github.com

    B+Tree DB with sub-second replication to 100+ nodes

    Hacker News15 pts

  4. Distributed Llama

    github.com

    Run LLMs on multiple devices in parallel

    Hacker News12 pts

  5. Cachegrand

    cachegrand.io

    a fast Redis-compatible KV-store, v0.2.1 released

    Hacker News12 pts