AI HARDWARE

–

20 October 2023 18h10

Calling all researchers! The @argonne_lcf AI Testbed is now accepting proposals for AI projects that can leverage the power of the new Groq system. Don't miss out on this opportunity to accelerate your research. Submit your project proposals to @argonne at http://
alcf.anl.gov/alcf-ai-testbed

Groq’s Speed Superpower: Tim’s Generative AI Workshop Talk

By

–

20 October 2023 17h26

"If speed was a superpower, Groq’s would be wearing a cape!" Check out Tim's talk here: https://
aixplain.com/blog/generativ
e-ai-workshop-recap/
…

Groq’s LLM Inference Hardware 10X Faster Than Nvidia

By

–

20 October 2023 17h26

"
@csTimSears dazzled us with a deep dive into @GroqInc
's cutting-edge SW/HW ecosystem. He showcased the lowest latency version of LLM inference hardware, which boasted a speed 10X faster than NVidia. The room was abuzz with questions and excitement, and rightly so."

→ View original post on X — @actuiafr

USA Imposes New Restrictions on Semiconductor Chip Manufacturers

By

@actuiafr

–

20 October 2023 17h07

USA: Government Unveils New Restrictions Imposed on Chip Manufacturers https://actuia.com/actualite/usa-le-gouvernement-devoile-les-nouvelles-restrictions-imposees-aux-fabricants-de-puces/
… #AI #ArtificialIntelligence

→ View original post on X — @jeremyphoward

H100 GPU Pricing Comparison Lambda Labs Alternative

By

@jeremyphoward

–

19 October 2023 21h35

I might be missing something – afaict they're 5x more expensive than lambda labs for H100 for instance

→ View original post on X — @nvidiaai

NVIDIA AI Enterprise Now Available on Oracle Cloud Marketplace

By

@nvidiaai

–

19 October 2023 21h15

In collaboration with @nvidia
, @Oracle announced that NVIDIA AI Enterprise and #NVIDIADGX Cloud is now available through the Oracle Cloud Marketplace. #AI #DataCenter Read the announcement now: https://
nvda.ws/3tHj1Pq

→ View original post on X — @linusekenstam

Figure 01 Humanoid Robot Revolution Accelerates

By

@linusekenstam

–

19 October 2023 20h50

This is not science fiction This is @Figure_robot 01 The humanoid robot revolution is about to kick into overdrive

Groq Unlocks FinServ AI with Speed and Throughput

By

–

19 October 2023 19h59

Stop by our table today at #STACSummit NY to find out how to unlock #FinServ #AI with best in class speed and throughput.

→ View original post on X — @predibase

LoRAX: Serve Hundreds Fine-Tuned Models Single GPU

By

@predibase

–

19 October 2023 19h13

Serving multiple #finetuned models typically requires dedicated, costly GPUs for each deployment—until now. Introducing LoRA Exchange (LoRAX): dynamically serve 100s of fine-tuned #LLMs on a single GPU w/out sacrificing throughput at a much lower cost.