NVIDIA's newest memory architecture for custom AI accelerators does something that no commercially available high-bandwidth memory standard has done before: it moves the memory controller off the ...

Longsys Electronics allocates 78% of its $903 million Hong Kong IPO to AI memory R&D as revenue surges 136% and net profit jumps 260-fold in H1 ...

A new point of contact between NVIDIA and custom XPUs, viewed from the placement of control circuits To what extent does ...

New GDDR7 memory packages could reach 32Gb and 48Gb densities between 2027 and 2028, according to a report from Golden Pig.

A new abbreviation could emerge with the introduction of upcoming AI accelerators: NVHBM. Nvidia is marketing this as a variant of manufacturer-customized High Bandwidth Memory (Custom HBM4). HBM4 ...

Montage Technology has introduced the M88MX6852, a CXL 3.2 Memory eXpander Controller (MXC) chip for AI infrastructure and data center applications. The device has entered trial production and has ...

CXMT, a linchpin in China’s drive to develop homegrown artificial intelligence technology, is aiming to raise nearly $10 billion in a blockbuster public offering in Shanghai. By Steve Lohr and Xinyun ...

Nvidia CEO Jensen Huang attends the Q&A session with the media during Nvidia/Japan AI Ecosystem Reception in Tokyo on July 16, 2026. Philip FONG/AFP via Getty Images NVIDIA's newest memory ...