AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
2min chapter
Parallelism and Acceleration for Large Language Models with Bryan Catanzaro - #507
The TWIML AI Podcast (formerly This Week in Machine Learning & Artificial Intelligence)
Is There a Play for for Quantization or Compression?
Are there things that you've learned with megaton that you see scaling down toa less large scale, employments like the d g x pods? And maybe another another angle to that is, is there a play for, or an element of the use of techniques like quantization or compression that you look at in connection with this project? Yes. Well, looking at memory band with is is always really important when optimizing a kind of low level details of a some softer like this and dum. That's important at large scale. It's also important at small scale. We know, we're big fans of the pytorch jit. So magatron is written in pytorch
00:00
Transcript
Episode notes
Get the Snipd
podcast app
Unlock the knowledge in podcasts with the podcast player of the future.
AI-powered
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