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 RuntimeWire Staff · Published · Updated

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.