General Compute taps Positron AI to split inference work between GPUs and memory-first chips
Photo: Crypto Briefing
The neocloud will run prefill on GPUs and hand decoding to Positron hardware, with first customer deployments expected in Q1 2027 General Compute has signed a strategic partnership with Positron AI that splits AI inference work between two kinds of hardware. GPUs will handle the prefill stage, and Positron’s memory-first accelerators will take over decoding. The companies announced the deal on October 20, 2026. First hardware deployments for customers are expected to come online in Q1 2027. Under the agreement, General Compute will buy Positron’s Atlas inference systems at cluster scale.
Source: Crypto Briefing
