🤗 Large ML models in production with HuggingFace CTO Julien Chaumond
The MLOps Podcast
00:00
Is There a Real Time Inference Package Support?
We have this product in in private beta, like any one should feel free to get in touch. Weare looking for, like a lot of a betatestar. A w, without diving too much into the details, it's built on top of so twere such as triton. I don't know if you've heard of triton, which is like a pretty call like onis optimi run time. And the last question we have from the community is from cha a about how do you plan to support a real time inference? Ah, do you have an inference package support to support the distilled or smaller models?
Transcript
Play full episode
