At Hot Chips 2026, Oxmiq Labs went into an analysis of HBF versus HBM in AI compute and where the buzzworthy HBF fits in the ecosystem
Apple launched the Apple Mac Mini M6 and Mac Studio M5 Ultra for those looking to do local AI with Apple's unified memory
We got a deep-dive on OpenAI Jalapeño at Hot Chips 2026 as the company rapidly built its own competitive AI accelerator
Hot Chips 2026 sees Google discussing its new eighth-generation TPU family for the technical crowd. One of the only hyperscalers to develop its own training hardware, the company has developed the TPU 8t for training, as well as the TPU 8i for inference
This year's Hot Chips conference includes a presentation from AI accelerator developer SambaNova, who is at the show to discuss their latest-generation RDU, the SN50
At Hot Chips 2026, Microsoft is going into new detail on Maia 200, their second-generation server AI inference processor
At Hot Chips 2026, wafer scale engine developer Cerebras is talking about the next generation of their giant accelerators, as well as how the company is going rack-scale thanks to their Nexus platform architecture
The newest member of NVIDIA's AI hardware family, at Hot Chips 2026 NVIDIA is diving into the use of LPUs as part of Vera Rubin clusters. The specialized chips from acquihire Groq are being tapped to offer significantly lower latency in the decode phase of inference
For Hot Chips 2026, Meta is at the show to discuss their AI inference accelerators. The MTIA family, the company has an ambitious roadmap to release 4 accelerators over the next couple of years
At Hot Chips 2026, NVIDIA showed how Spectrum-X and a multiplane network is its vision for AI Factory networks