128 chips, 1.7 exaFLOPS, and 27 TB of HBM give Altman and crew a leg up over Blackwell, and maybe even Rubin

Gemma 4 31B performance tests offer a best-case scenario for next-gen dataflow accelerators

128 GB of memory! In this economy?

: Take those token limits and shove them by vibe coding with a local LLM

Review: An $899 CPU? In this economy?

Review: An $899 CPU? In this economy?

Review: More cores, higher clocks, and lower prices? What's not to like?

Kettle: Cyber is no longer the hush-hush thing it used to be, as team Trump invades Iran with hackers taking the lead

Hands On: Two tiny boxes, 128 GB apiece – but very different strengths

Hands On: Two tiny boxes, 128 GB apiece – but very different strengths

re:invent: The homegrown chips now account for half of all new CPUs added to AWS over the past three years

Re:Invent: Meanwhile, Trainium3 makes its debut promising million-chip training clusters

hands on: $12K machine promises performance that can scale to 32 chip servers and beyond but immature stack makes harnessing compute challenging

SC25: EuroHPC's biggest iron still has more to give with Universal Cluster expansion expected to come online next year

: Chocolate Factory's homegrown silicon boasts Blackwell-level perf at massive scale

hands on: This relatively-affordable AI workstation isn’t about going fast; it’s about doing everything well enough

ai-pocalypse: Consultancy says machine learning advice is making bank

Analysis: Why strap pricey, power-hungry HBM to a job that doesn't benefit from the bandwidth?

: Engineers wrangle 55 TB restore and traffic replay as millions of messages queue up

Hands on: Everything you need to know to build, run, serve, optimize and quantize models on your PC

: Burger slinger gets a McRibbing, reacts by firing staffer who helped

: Rami Sinno led Trainium and Inferentia development at Amazon

: It's that or a replacement for its aging H200 NVL PCIe cards

Comment: Spy vs spy in the chips

: When one GPU translates into three to five of the fastest switch ports money can buy, can you blame them?

Analysis: Gotta pay for all those GPUs somehow

Analysis: Decision to use MXFP4 makes models smaller, faster, and more importantly, cheaper for everyone involved

: Chinese AI model dev still plans to use homegrown silicon for inferencing

: The world's most powerful known supercomputer stretches its legs with some life-saving science