3min chapter

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence) cover image

Multi-Device, Multi-Use-Case Optimization with Jeff Gehlhaar - #587

The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)

CHAPTER

The AI Model Efficiency Toolkit

The AI model efficiency toolkit is kind of at the center of this right. We have tools that plug into PyTorch and plug into TensorFlow, add a little bit of extra to your training pipeline and then condition the model during training to be quantization aware. So you would run it through post training quantization. This produces a representation of the model in this Qualcomm AI engine direct format. Think about it like an intermediate representation. Once we have it in that common representation, you can then write wherever you want.

00:00

Get the Snipd
podcast app

Unlock the knowledge in podcasts with the podcast player of the future.
App store bannerPlay store banner

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode

Save any
moment

Hear something you like? Tap your headphones to save it with AI-generated key takeaways

Share
& Export

Send highlights to Twitter, WhatsApp or export them to Notion, Readwise & more

AI-powered
podcast player

Listen to all your favourite podcasts with AI-powered features

Discover
highlights

Listen to the best highlights from the podcasts you love and dive into the full episode