Sign inLaunch

OpenLake

Storage engine for KV-cache offload and LLM training

🧱 LLMs & InfrastructureOpen SourceY▲ 35 on HNLaunched September 25, 2026

OpenLake is a high-performance storage engine for LLM inference and GPU training. Its Infinity Core I/O Engine delivered 6.72 GiB/s writes and 11.55 GiB/s reads in the MLPerf Storage v3.0 Llama 3.1 8B checkpointing benchmark through its S3 API. First shared by its maker on Show HN: https://news.ycombinator.com/item?id=49578727

✨ The overview, FAQ and details below were drafted by AI from the product's own website and haven't been reviewed by the maker yet. Are you the maker? Claim this listing to review and edit them.

Overview

Who is it for?

ML infrastructure teams running LLM training and inference.

Problem

Storage throughput limits checkpointing and KV-cache offload as AI workloads scale.

Solution

A storage engine with an S3-compatible API built for AI training and inference I/O.

What makes it unique

OpenLake reports the highest read and write bandwidth among published Closed-division S3 results for that MLPerf checkpointing workload.

OpenLake FAQ

What did OpenLake achieve in MLPerf Storage v3.0?

6.72 GiB/s writes and 11.55 GiB/s reads on Llama 3.1 8B checkpointing with one client node, the highest among published Closed-division S3 results.

How do I access it?

Through an S3 API interface.

Details

Pricing
Open Source
Built for
Developers
Platforms
API
Alternative to
Amazon S3

Hunted by AI Launch Team

Discussion (0)

Sign in to join the discussion.