GPT-2 etched directly into silicon let’s go 🙂
COMPUTING
-
M4 Mac Desktops to Support 512GB Unified Memory
By
–
Wow, might be worth waiting for the M4 then: https://
macrumors.com/2024/04/11/m4-
ai-chips-late-2024/
… "M4 versions of the Mac desktops could support as much as 512GB Unified Memory, which would be a marked jump over the current 192GB limit." -
Latest Advances in Confidential Computing for Data Protection
By
–
The Latest in #Data Protection? Confidential Computing
by @booksnfreshair @insightdottech Read more: https://
buff.ly/3OSOnud #BigData #ArtificialIntelligence #MI #AI cc: @pbalakrishnarao @yvesmulkers @kuriharan -
HuggingFace Trainer DistributedDataParallel Gradient Bug Fix
By
–
ok so, it was a gradient bug. let me explain with the huggingface trainer, when training on multiple GPUs, sometimes the model is stored as an nn.Module, but sometimes it’s wrapped in this DistributedDataParallel thing I was inadvertently forwarding on the nn.Module in
-
DeepSpeed optimization successfully implemented for AI training
By
–
@winglian wrangled deepspeed till it worked
-
Microsoft Optimizes Bing Ads with NVIDIA Triton Inference
By
–
DYK – By using Triton Inference Server, Microsoft Bing personalized ads to users applying sophisticated techniques to do more work in less time with less computer memory. Read their story to learn more > https://
nvda.ws/3UbmeBw #AI #inference #NVIDIATriton By using Triton -
Avi Wigderson on Theory of Computation and Ideas
By
–
I had a wonderful time talking with this year's winner of the A.M. Turing Award for lifetime achievement in computer science, Avi Wigderson. Wigderson has really fascinating points to make about how the Theory of Computation has come together, about how ideas lead to
-
Unlock Embedded Applications with Altera FPGA Technology
By
–
Unlock Embedded Applications with Altera FPGA
— Ronald van Loon (@Ronald_vanLoon) 11 avril 2024
by @Ronald_vanLoon & Ben Lee |
Get started now: https://t.co/8dTCzGJkwg#AlteraAmbassador @AlteraFPGA_ #WeAreAltera #AcceleratingInnovators #LeapIntoTheFuture #FPGA #Agilex #AlteraAtEmbeddedWorld #EW24 #Embeddedworld
Cc:… pic.twitter.com/Z2qYAKFv6TUnlock Embedded Applications with Altera FPGA
by @Ronald_vanLoon & Ben Lee | Get started now: https://
bit.ly/43Qz5wd #AlteraAmbassador @AlteraFPGA_ #WeAreAltera #AcceleratingInnovators #LeapIntoTheFuture #FPGA #Agilex #AlteraAtEmbeddedWorld #EW24 #Embeddedworld Cc: -
Edge AI Inference Energy Efficiency Through At-Memory Architecture
By
–
Scaling #AI to the edge sustainably is a challenge. Our CEO Chris Walker joins @MoorInsStrat podcast to explain how our unique at-memory architecture radically cuts data movement energy consumption for edge AI inference. Listen now: https://
x.com/i/broadcasts/1
YqGoDaakVQJv
… -
Pro Gamers Enhance NVIDIA Software Quality Assurance Testing
By
–
For some NVIDIANs, it's always game day. Discover how pro gamers bolster our software quality assurance testing. #NVIDIAlife