Galaxy reported that MLCommons published MLPerf Storage v3.0 results, adding a KV cache test measuring storage performance for LLM inference cache reads and writes alongside a vector database test covering indexing and querying workloads.
Published
Signal category
Research & Knowledge
Quote
“MLCommons published MLPerf Storage v3.0 results, adding a KV cache test that measures storage performance for LLM inference cache reads and writes, alongside a vector database test covering indexing and querying workloads.”
— Galaxy team
Company
Galaxy
AI readiness starts with data readiness.
- Industry
- Software Development
- Location
- New York, US
- Company size
- 6 employees
Galaxy embeds as a forward-deployed team, working on top of your existing systems and turning fragmented data into structured context, giving your teams and AI agents a shared understanding of your organization. That means faster decisions, reliable AI workflows, and less time maintaining data infrastructure. We are backed by Caffeinated, Bungalow, and Crew Capital, with a team that has built critical data infrastructure at Flock Safety, Bloomberg, Unify, Blackstone, and Attentive.
Founded 2025