Understand this story
On November 3, 2026, SambaNova and Supermicro announced a partnership under which Supermicro will manufacture, sell, and support AI inference systems combining NVIDIA GPUs with SambaNova SN50 reconfigurable dataflow units, with an initial plan to procure 10,000 SN50 chips. According to Unite.AI, the system divides work by inference stage: GPUs handle compute-intensive prefill, while SN50 RDUs handle memory-intensive decode; SambaNova says this is faster and more efficient than using either hardware alone. The products will first target NeoClouds and sovereign clouds, then expand to enterprises building their own data centers; the two companies expect to offer more high-performance inference capacity in 2027. No further progress has been disclosed yet.
AI-generated from public reports
Latest development · Report
Supermicro to Produce and Sell AI Inference Systems Powered by SambaNova SN50Developments
1 confirmed developments
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 4
Unite.AI
Supermicro to Produce and Sell AI Inference Systems Powered by SambaNova SN50
SambaNova and Supermicro announced the partnership on November 3, 2026, under which Supermicro will produce, sell, and support AI inference systems combining NVIDIA GPUs with SambaNova SN50 reconfigurable dataflow units, with initial plans to purchase 10,000 SN50 chips. The system divides work by inference stage, with GPUs handling the compute-intensive prefill and SN50 RDUs handling the memory-intensive decode; SambaNova says this is faster and more efficient than using either hardware alone. The products will first target NeoClouds and sovereign clouds, then expand to enterprises building their own data centers, and the two companies expect to offer more high-performance inference capacity in 2027.