1min snip

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0 cover image

Doing it the Hard Way: Making the AI engine and language 🔥 of the future — with Chris Lattner of Modular

Latent Space: The AI Engineer Podcast — Practitioners talking LLMs, CodeGen, Agents, Multimodality, AI UX, GPU Infra and all things Software 3.0

NOTE

Challenges with On-Device ML and Quantization

On-device ML work has mainly focused on quantization, which uses hacks to represent floating point numbers with limited bits. Although it may seem funny to nerds, it is a flexible and useful hack. The challenge lies in the hard-coded implementation of these hacks, making it difficult to compose different models. GgML, a project with smart people, requires significant rework before accommodating novel models. Not many people know the necessary C++ to work on this.

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