DiscoverIndustrial AI PodcastNeurIPS 24: Faster than Flash Attention
NeurIPS 24: Faster than Flash Attention

NeurIPS 24: Faster than Flash Attention

Update: 2024-12-18
Share

Description

Peter and Robert look back on the NeurIPS in Vancouver. They talk about the fuel of the AI community, new phases of AI and Hochreiter reports on his xLSTM 7B model and its special features. According to Hochreiter, xLSTM is not just another LLM.

Thanks for listening. We welcome suggestions for topics, criticism and a few stars on Apple, Spotify and Co.


Our guest: Prof. Dr. Sepp Hochreiter


Github NXAI https://github.com/NX-AI


Huggingface xLSTM https://huggingface.co/NX-AI/xLSTM-7b


History of AI by Jürgen Schmidhuber https://people.idsia.ch/~juergen/deep-learning-history.html


We thank our partner SIEMENS


Our event in January in Frankfurt: more

Comments 
loading
00:00
00:00
1.0x

0.5x

0.8x

1.0x

1.25x

1.5x

2.0x

3.0x

Sleep Timer

Off

End of Episode

5 Minutes

10 Minutes

15 Minutes

30 Minutes

45 Minutes

60 Minutes

120 Minutes

NeurIPS 24: Faster than Flash Attention

NeurIPS 24: Faster than Flash Attention

Robert Weber / Peter Seeberg