HPE Alletra MP X10000 Release 4 doubles cluster size and unifies file+object

HPE released Alletra MP X10000 Release 4: nodes and JBOFs increased from 8 to 16, maximum capacity grew from 11.8 to about 23 PB, and NFS file system was added to object storage. RDMA and Nvidia GPU Direct for KV cache are now supported.

• Cluster scales from 8 to 16 nodes and JBOFs, capacity up to ~23 PB
• NFS file system added to object storage — a unified system
• RDMA and Nvidia GPU Direct for KV cache speed up inference
• Omdia: up to 20x faster time to first token and up to 17x higher throughput