HPC & Quantum
27 subscribers
11.4K photos
668 videos
3 files
30.7K links
Download Telegram
HPC Guru (Twitter)

What We Learned from a Year of Building with #LLMs (Part I)

“Over the past year, the six of us have been building real-world applications on top of LLMs. We realized that there was a need to distill these lessons in one place”

https://www.oreilly.com/radar/what-we-learned-from-a-year-of-building-with-llms-part-i/

#GenAI
HPC Guru (Twitter)

#LLMs have the potential to streamline the labor-intensive process of hardware development

LLM4HWDesign contest aims to harness community efforts to develop an open-source, large-scale, and high-quality dataset for hw code generation

https://nvlabs.github.io/LLM4HWDesign/

#AI via @DrJimFan
HPC Guru (Twitter)

RT @thoefler: Humanity is transitioning from the information age to the age of computing driven by #HPC. Soon, economic power will be with the ones who compute fastest and cheapest.

#AI and #LLMs are big applications, but simulations and scientific discovery will equally benefit. https://twitter.com/TheOfficialACM/status/1820461030587220193#m
HPC Guru (Twitter)

#RAG enhances the accuracy of #LLMs by retrieving information from external sources

This blog post explores the impact of increased context length on the quality of RAG applications

https://www.databricks.com/blog/long-context-rag-performance-llms

#GenAI via @NaveenGRao
HPC Guru (Twitter)

SigLLM: In a new study, @MIT researchers found that #LLMs hold the potential to be more efficient anomaly detectors for time-series data

Importantly, these pretrained models can be deployed right out of the box

https://news.mit.edu/2024/researchers-use-large-language-models-to-flag-problems-0814

#AI #GenAI
HPC Guru (Twitter)

Intro to #Al-driven #Science on #Supercomputers

@argonne_lcf hosts a series of courses on understanding the fundamentals of #LLMs and their scientific applications

Register by Sept 29

https://events.cels.anl.gov/event/538/

#HPC