myrtle.ai VOLLO accelerator sets new STAC-ML records for gradient-boosted trees
myrtle.ai announced its VOLLO inference accelerator has set new records on STAC-ML Markets benchmarks for gradient-boosted trees, cutting p99 latency by over 30% and raising throughput 5x. The STAC-audited results showed sub-2µs p99 latency and up to 50 million inferences per second.