Microsoft announces Maia 200, a powerful new chip for AI inference

LLM On-Premise Observatory

Hardware, stack, governance, and reference architectures for local AI.

Microsoft launches Maia 200 AI chip, mass production progress draws attention

Microsoft has announced Maia 200, a new chip designed specifically for artificial intelligence workloads. The company is moving towards mass production, marking

Microsoft's Maia 200 chip targets AI inference cost advantage, not Nvidia rivalry

Microsoft unveiled Maia 200, a chip designed to optimize AI inference costs. The goal is not to compete directly with Nvidia, but to offer a more cost-effective

Meta accelerates development of dedicated AI inference chips

Meta joins the hyperscaler trend in developing dedicated AI inference chips, aiming to diversify its reliance on a single vendor and optimize specific workloads

Intel taps SambaNova for AI inference push via partnership and minority stake

Intel is partnering with SambaNova Systems, acquiring a minority stake, to strengthen its AI inference capabilities. The collaboration aims to enhance Intel's h

Microsoft cuts Maia 200 chip costs by 30%

Microsoft has announced a 30% cost reduction for its Maia 200 chip, amid strong demand and GPU shortages. This move could make AI solutions more accessible, esp

ORL pushes diffusion LLMs to 2,788 tokens/s on a single RTX 5090

Open source sovereignty: the boring work of making it real

Bolt Graphics seeks $100 million to challenge Nvidia and AMD with the Zeus GPU

DeepSeek-V4-Flash on 4x Radeon AI PRO R9700: the 79 tok/s configuration that finally works

GNOME Mutter Improves Damage Tracking for Secondary GPU Copy Buffers

AMD W7900 and LFM2.5: A Concrete Signal for On-Premise LLM