AMD to deliver 6 GW of AIPs to Meta
How many is 6 GW, and where will Meta put them?
Can AI save science?
AI processors using dataflow look very promising.
Sunrise releases next-generation inference GPU, Qiwang S3
Is shifting its architecture toward inference-first design.
Neurophos CIM promises super high performance at a fraction of the power
AI processing at the speed of light.
Interview with Steve Roddy, chief marketing officer, Quadric, Inc.
Quadric’s bet on software-first NPUs starts to pay off.
New Xeon for Workstations (Granite Rapids): Here to protect Intel’s market position in desktop workstation
What is new, what is better, and, most importantly, is it enough?
Semidynamics announces 3 nm inference tape-out and a full-stack systems roadmap
Semidynamics moves to offer silicon.
Interview with MIPS: Drew Barbier and James Prior
MIPS’ unlikely rise to deliver RISC-V at ‘foundry scale.’
$30 million more invested in AIP start-ups
Quadric gets the latest injection, but far from last.
Microsoft’s Maia 200 inference AIP
Triples computational throughput, reduces inference latency and costs per token.
Ainekko merges with Veevx after Esperanto pickup
Combining open-source AIPs and iRAM.
The proof is in the shipping
Furiosa sends 4,000 AIP AIBs off to work.