---
format: "aidr-story-markdown/v1"
id: "141e745bc76fcf885e7a299f887f9b238dc3a706b3802c9d5d56f5d96f990810"
canonical_url: "https://aidr.today/141e745b?lang=en"
title: "General Compute Splits AI Inference Between GPUs and Positron Hardware"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-10-20T17:23:46.000Z"
category: "Infra"
topics: ["inference"]
source_urls: ["https://huggingnews.com/ai/general-compute-splits-ai-inference-between-gpus-and-positron-hardware-99973f5c","https://marketbrief.now/ai/general-compute-splits-ai-inference-between-gpus-and-positron-hardware-99973f5c"]
summary: "General Compute is purchasing Atlas and Titan systems from Positron AI to scale its heterogeneous cloud infrastructure, enabling the prefill stage of AI inference to run on GPUs and the decode stage to run on Positron's memory-first systems, with the hardware going live in Q1 2027."
---

# General Compute Splits AI Inference Between GPUs and Positron Hardware

> [Open the canonical story](<https://aidr.today/141e745b?lang=en>)

**Published:** 2026-10-20T17:23:46.000Z
**Category:** Infra
**Topics:** inference

## Summary

General Compute is purchasing Atlas and Titan systems from Positron AI to scale its heterogeneous cloud infrastructure, enabling the prefill stage of AI inference to run on GPUs and the decode stage to run on Positron's memory\-first systems, with the hardware going live in Q1 2027\.

## Sources

- [Story source](<https://huggingnews.com/ai/general-compute-splits-ai-inference-between-gpus-and-positron-hardware-99973f5c>)
- [Story source](<https://marketbrief.now/ai/general-compute-splits-ai-inference-between-gpus-and-positron-hardware-99973f5c>)