Vsora CEO: We are the European Nvidia for AI inference
Khaled Maalej says his inferencing chip flies the flag for Europe's compute sovereignty
News - High Bandwidth Memory
The latest news on networking, cloud, and AI infrastructure
-
SK Hynix banks on optical interconnects to defend its HBM crown
South Korean giant backs light to unlock next-gen AI memory performance
-
SK Hynix, Sandisk unveil first standard for high-bandwidth flash
NAND flash alternative to HBM redefine low latency for AI inference infrastructure
-
SK Hynix secures multiyear Nvidia deal to develop next-gen AI memory
Co-engineering pact expanded as Nvidia looks to ensure future hardware to sustain AI infrastructure buildout
-
Samsung ships ‘industry-first’ 12-layer HBM4E samples, lauding AI performance boost
Next-gen high bandwidth memory product offer a 20% speed increase and 16% greater energy efficiency for AI computing and hyperscale infrastructure
-
RAM-raid profit frenzy sees Micron, SK Hynix hit $1T market caps
Memory makers laugh all the way to the bank as profits surge
-
Nvidia's Rubin GPUs hit the brakes as HBM4 memory drought threatens Jensen’s supply chain magic: report
Next-gen Rubin shipments to drop 7 points as SuperNIC and liquid cooling ‘challenges’ stack up
-
Applied Materials and SK Hynix to co-develop next-gen DRAM, HBM at $5B Silicon Valley R&D facility
SK Hynix has become a founding partner of the EPIC Center, slated to open later this year
-
DeepSeek looks to offload simple LLM tasks to save billions of parameters
'Conditional memory' concept moves simple lookups from expensive GPU memory to cheaper CPU RAM
-
AI inference crisis: Google engineers on why network latency and memory trump compute
Researchers propose low-latency topologies and processing-in-network as memory and interconnect bottlenecks threaten inference economic viability