THE WORLD IS NOT STANDING STILL.RSS
BIG CHANGE.
BIG CHANGE, one tap away
BIG CHANGE, one tap away

Make room for the big picture.

Add BIG CHANGE to your home screen or desktop. It opens in its own window, with the latest stories when you’re online.

iPhone & iPad
Open bigchange.ai in Safari. Tap Share, then Add to Home Screen. Turn on Open as Web App if shown, then tap Add.
Android
Open bigchange.ai in Chrome. In the browser menu, choose Install app or Add to Home screen.
Desktop
In Chrome or Edge, use the install icon in the address bar or the browser’s app menu. In Safari on Mac, choose File → Add to Dock.

Markdown edition

# Supermicro plans inference systems with SambaNova chips

> The planned racks would divide prompt processing and response generation between different chips.

By BIGCHANGE.AI Editorial

Published: 2026-11-04T02:44:38.695Z
Updated: 2026-11-04T02:44:38.695Z
Canonical: https://bigchange.ai/blog/supermicro-sambanova-split-inference-systems

![Conceptual illustration of a generic server cabinet in a data-centre aisle, with cables routed along overhead trays.](https://bigchange.ai/api/media/file/cuda-shared-compute-hero-v1.png)
AI-generated conceptual illustration by BIG CHANGE.

SambaNova says Supermicro plans to build and sell inference systems combining NVIDIA GPUs with its SN50 chips. The initial plan covers 10,000 SN50 chips.

## The big change

- Splitting phases can match hardware to different compute and memory demands.
- Supermicro would deliver and support the systems; SambaNova would tune models.
- The chip count is a plan, not confirmed shipments.

## Why split inference?

A language model processes a prompt before generating response tokens. The [Splitwise research paper](https://arxiv.org/abs/2311.18677) found prompt processing compute-intensive and token generation limited by memory under its studied conditions. Separating them lets operators allocate hardware suited to each phase while running one service.

In the [November 3 announcement](https://sambanova.ai/press/sambanova-and-supermicro-partnership), the partners propose NVIDIA GPUs for prompt processing and SambaNova’s dataflow chips for generation. This does not prove that their rack is faster or more efficient.

SambaNova’s [earlier architecture account](https://sambanova.ai/blog/hot-chips-2026-dataflow-at-scale) describes on-chip memory and dataflow execution in the SN50. It is a vendor description, not a measurement of the proposed combined rack.

Splitting stages requires transferring request state. Splitwise studied transfer overhead in its own system; it did not measure this proposed configuration. The partners have not supplied comparable independent results.

The companies plan to start with neoclouds and sovereign clouds, then enterprises. Prices, delivery dates and confirmed customer deployments were not disclosed.

## Sources

- [SambaNova partnership announcement](https://sambanova.ai/press/sambanova-and-supermicro-partnership) — Company announcement and planned system responsibilities.
- [Splitwise research paper](https://arxiv.org/abs/2311.18677) — Research on separating inference phases and transfer costs.
- [SambaNova SN50 architecture](https://sambanova.ai/blog/hot-chips-2026-dataflow-at-scale) — Earlier company account of its dataflow chip.