Myrtle.ai's VOLLO hits 50M tree inferences per second in STAC test

On an AMD Alveo V80LL and Blackcore server, VOLLO delivered sub-2-microsecond p99 latency across three tree models; STAC lists it as ML-20260925, while myrtle.ai's release cites MRTL2026905.

By · Published · Updated

An unbranded server and accelerator card sit beside three branching decision-tree forms, illustrating myrtle.ai’s VOLLO STAC test.

On an AMD Alveo V80LL and Blackcore server, VOLLO delivered sub-2-microsecond p99 latency across three tree models; STAC lists it as ML-20260925, while myrtle.ai's release cites MRTL2026905.