Instinct MI450X

Latest about Instinct MI450X

AMD denies report of MI455X delays as Nvidia VR200 systems are rumored to arrive early — company says Helios systems 'on target for 2H 2026'

By Anton Shilov Published

Is UALink to blame?

Artificial Intelligence
AMD Helios rack system.
AMD touts Instinct MI430X, MI440X, and MI455X AI accelerators and Helios rack-scale AI architecture at CES

By Anton Shilov Published

AMD reveals additional details about its strategy for AI and HPC deployments this year with EPYC 'Venice' and 'Venice-X' CPUs as well as Instinct MI430X, MI440X, and MI455X accelerators.

Artificial Intelligence
AMD
AMD's Linux kernel patches suggest enablement of Instinct MI400-series GPU accelerators

By Anton Shilov Published

AMD begins hardware enablement for GFX 12.1 IP, which could point to next-generation Instinct MI400-series GPUs, or future integrated GPUs based on the RDNA 4 architecture.

GPUs
AMD
Instinct MI450 is officially the first AMD GPU to launch with TSMC's cutting-edge 2nm tech

By Anton Shilov Published

OpenAI will be among the first to get these accelerators.

Artificial Intelligence
OpenAI signs AMD deal for 6GW of AI GPUs with a massive equity kicker, OpenAI to obtain up to 160 million AMD shares at one cent apiece

By Luke James Published

Premium OpenAI has secured up to 6 gigawatts of AMD GPU compute in a landmark supply agreement that could see the ChatGPT maker take a 10% stake in AMD.

Premium
Nvidia wants 10Gbps HBM4 to blunt AMD’s MI450, report claims

By Luke James Published

Nvidia is reportedly pressing its memory vendors to push beyond JEDEC’s official HBM4 baseline, reportedly requesting 10Gb/s-per-pin stacks for its 2026 Vera Rubin platform.

GPUs
AMD
AMD preps rack-scale Instinct MI450X IF128 for 2026 release

By Anton Shilov Published

News Analysis AMD is set to launch its first rack-scale MI450X IF128 AI systems in 2026. The company hopes it will challenge Nvidia's VR200 NVL144 with up to 128 GPUs.

News Analysis
AMD
AMD to split flagship AI GPUs into specialized lineups for AI and HPC

By Anton Shilov Published

But there is a major catch.

GPUs