Thank you @HPCsharp @PASC_Conference https://
arxiv.org/abs/2208.05419 Our work was first to do weather forecasts at 25km spatial resolution with 10^4-10^5 speedups using Fourier neural operators. Recently we added spherical harmonics for stable long rollouts https://
arxiv.org/abs/2306.03838
COMPUTING
-
Fourier Neural Operators Achieve 10^4-10^5 Speedups Weather Forecasting
By
–
-
Fourier Neural Operators Enable 25km Weather Forecasting
By
–
Thank you @PASC_Conference https://
arxiv.org/abs/2208.05419 Our work was first to do medium-range weather forecasts at 25km spatial resolution with 10^4-10^5 speedups using Fourier neural operators. Recently we added spherical harmonics for stable long rollouts https://
arxiv.org/abs/2306.03838 -
Nvidia dominates AI benchmarks while Intel Habana gains ground
By
–
Nvidia sweeps AI benchmarks, but Intel brings meaningful competition Habana came very close on several tests of 8-way systems. @MLCommons $NVDA $INTC $AMD #AI #MLPerf #GPU #CPU
-
DGX Station Failure and Hardware Redundancy Considerations
By
–
Still very happy with our @LambdaAPI cluster, so my personal DGX station dying isn’t critical path, but I liked having some redundancy in capabilities. I sometimes think about the merit of having a stockpile of physical hardware in case something crazy happens in the volatile AI
-
Software optimization and co-design for H100 GPU maximum potential
By
–
yea, I expect a healthy amount of software work and co-design to use the H100 to its maximum potential!
-
Edge Cloud Infrastructure Requirements Industry 4.0 Era
By
–
Don't miss the keynote session on Edge and Cloud Infrastructure Requirements in the #Industry40 Era, sponsored by @SchneiderElec
! Get equipped with invaluable insights from industry experts. Join us LIVE! https://
ow.ly/8QTa50OZoHS #sponsored #se_iiot #IIoTWorldDay #energy -
SambaNovaAI DataScale SN30 Training Workshop at Argonne
By
–
Register now for an exciting training workshop introducing users to the @SambaNovaAI DataScale SN30 deployed at the @argonne_lcf AI Testbed. This workshop is targeted at universities, national labs, and industries working on open science. https://
alcf.anl.gov/events/sambano
va-ai-training-workshop-0
… Spread the -
Deploy Cohere Models on AWS SageMaker Studio Securely
By
–
Cohere’s models are also available via Amazon SageMaker. This provides a solution for deploying use cases in a private and secure environment. In this module, you’ll learn how to create a product description generator endpoint on SageMaker via Amazon SageMaker Studio.
-
H100 Training Speed Triples A100 with FP8 Optimization
By
–
As @MosaicML showcased in April, on GPT training H100 is ~3x the speed of A100, if you use FP8 training, which is both seriously impressive and grounds you in relative improvement versus the previous generation! https://
mosaicml.com/blog/coreweave
-nvidia-h100-part-1
…