PlanetScale announces high-performance cloud hosting for Vitess and Postgres using locally-attached NVMe storage to deliver unlimited IOPS and horizontal scaling.
Sick of slow databases? Our locally-attached NVMe storage unlocks unlimited IOPS, bringing data center performance to the cloud while saving you money. Available for Postgres and MySQL in AWS or GCP.
Anyscale demonstrates a 20x speedup in cross-region training data reads by using Alluxio NVMe caching with Ray Data, showing warm cache reads drop from 4,241 to 208 seconds for 1TB.
Researchers propose Prefill-as-a-Service (PrfaaS), a system that offloads long-context prefill to remote compute-dense clusters and streams KVCache over commodity Ethernet, enabling independent scaling and 32-54% higher throughput for a 1T-parameter hybrid model.
This article explains how Databricks' Lakebase architecture achieves a 5x improvement in Postgres write throughput by disabling Full Page Writes (FPW) and leveraging stateless compute with distributed storage.
The author explains how they built a compute platform capable of launching millions of sandboxes per second in constant time, focusing on decoupled scheduling and capacity aggregation using Cassandra and S3.
MIT researchers have developed Sandook, a software-based system that improves data center storage performance by simultaneously addressing three sources of variability in SSDs, nearly doubling efficiency compared to traditional methods.