About us
We measured the latency budget and found most of it was ours
Vectorplay began as a research project into where the milliseconds in cloud gaming actually go.
Origin
It was never the network
Everyone blames the internet. We instrumented the whole chain and found that on a decent connection, network round trip was about a third of the added latency — the rest was encoder queueing, GPU sharing and a client that buffered defensively. All three are engineering choices, and all three are fixable.
- Whole GPUs, never partitioned
- Latency published per region and remeasured weekly
- Fair-use limits stated as numbers, not as 'unlimited'
A latency measurement project
Instrumenting the whole chain.
First region
Frankfurt, 200 GPUs, invite only.
QUIC datagram transport
Loss stops meaning stall.
AV1 encode
Bandwidth requirement falls by a third.
14 regions
12,000 GPUs, 17 ms median added latency.
How we work
Boring on purpose
We would rather run software that is three years old and understood than something new that pages us at 04:00.
Own the path
We buy transit from multiple carriers and peer directly wherever it is possible, so a single bad hop is never a single point of failure.
Write it down
Every incident gets a public write-up. Every design decision gets an RFC. Institutional memory beats heroics.
Some of the people behind it
A quarter of the company has been here since the first rack.
We are hiring
Remote-first across EU time zones, with a small office network for people who prefer one.