Meryem Arik on LLM Deployment, State-of-the-art RAG Apps, and Inference Architecture Stack

from InfoQ 3 weeks ago

I'm the co-founder and CEO of TitanML. And what we do is we build infrastructure to help regulated industries deploy generative AI within their own environments.
InfoQhttps://www.infoq.com/podcasts/llm-rag-inference-architecture-stack/

There was this really big gap between what was possible in the research literature and what enterprises were actually able to achieve.
InfoQhttps://www.infoq.com/podcasts/llm-rag-inference-architecture-stack/

Read at InfoQ

#generative-ai #regulated-industries #data-privacy #support-infrastructure

[

]

[

...

]

Meryem Arik on LLM Deployment, State-of-the-art RAG Apps, and Inference Architecture StackMeryem Arik on LLM Deployment, State-of-the-art RAG Apps, and Inference Architecture Stack Briefly

Meryem Arik on LLM Deployment, State-of-the-art RAG Apps, and Inference Architecture Stack
Meryem Arik on LLM Deployment, State-of-the-art RAG Apps, and Inference Architecture Stack
Briefly