2025-10-15
CRN
4 related
Intel unveils Crescent Island, a data center GPU “power- and cost-optimized” for AI inference, featuring its Xe3P microarchitecture and 160GB of LPDDR5X memory
Dylan Martin / CRN :
2023-09-12
CRN
9 related
Nvidia claims TensorRT-LLM will double the H100's performance for running inference on leading LLMs when the open-source library arrives in NeMo in October
Dylan Martin / CRN :
2022-11-02
The Register
4 related
Intel says its next-gen Sapphire Rapids Xeon chips are slated for January 2023, after a spate of delays dating back to 2021, another boon for AMD's server chips
Dylan Martin / The Register :
2022-05-07
The Register
Internal documents: Intel plans to launch a software platform this fall, codenamed Sonoma Creek, that will simplify and speed up computer vision model training
Dylan Martin / The Register : Tweets: @quinnypig . Thanks: @dylanljmartin Tweets: Corey Quinn / @quinnypig : That's an internal Intel roadmap, so I'm very curious to see what happens when they releas...
2019-11-18
CRN
5 related
Intel unveils plans for a 7nm Xe GPU, codenamed Ponte Vecchio, meant to rival Nvidia in handling datacenter AI workloads, but fails to give a release window
Nvidia can shake off rivals that have complicated and untested AI solutions Mark Hachman / PCWorld : Intel debuts Ponte Vecchio, its first Xe GPU for servers Paul Alcorn / Tom's Hardware : Intel Annou...
2018-08-27
CRN
1 related
Q&A with AMD CTO Mark Papermaster on the company's bet on 7nm instead of 10nm as Intel's chips face delays, plans to win market share in the server space, more
Dylan Martin / CRN :
Loading articles...