Digital Humans: NVIDIA Announces NIMs 🤯 Containerized AI Microservices

Рет қаралды 2,503

Ай бұрын

In this video, you'll learn about NVIDIA's new breakthrough: containerized AI microservices, called NIMs:
NVIDIA NIM (NVIDIA Inference Microservices) is a set of easy-to-use microservices for accelerating the deployment of foundation models on any cloud or data center infrastructure.
♥️ Join my free email newsletter to stay on the right side of change:
👉 blog.finxter.com/email-academy/
Also, make sure to check out the AI and prompt engineering courses on the Finxter Academy:
👉 academy.finxter.com
🚀 Prompt engineers can scale their reach, success, and impact by orders of magnitude!
You can get access to all courses by becoming a channel member here:
👉 / @finxter

Пікірлер: 10

@SamiSabirIdrissi Ай бұрын

I found this video extremely helpful. Thank you for taking the time to create this video. I find it really amazing. Now I need to shift my focus and start using NIM and the models it comes with. Thank you!!

@finxter Ай бұрын

Thanks 👍 yeah let's see if Nims will be the breakthrough success or something else that's very similar like OpenAI GPTs. It's all the same idea though, digitized scalable boxed human-like experts

@johnkost2514 Ай бұрын

Mozilla has a more convenient LLM format known as LlamaFile. It works across like six (6) operating systems. It's pretty cool as well for quick deployment.

@finxter Ай бұрын

Thanks!

@tusharbborse6975 Ай бұрын

dayumm

@finxter Ай бұрын

facts

@user-wr4yl7tx3w Ай бұрын

why microservice instead of cloud?

@finxter Ай бұрын

Edge computing will be a thing for a simple reason: inference latency. We humans have an inference machine in our head so we can timely react to changing environments. Similarly, humanoids and self-driving cars will have local inference. In this case, the microservice abstraction is more suitable because you can run a microservice on an edge inference device - or the cloud - without changing the API calls in your code.