High Signal Podcasts Evidence ledger
Method
Browse
How the evidence works
← All source episodes

Latent Space / episode intelligence

LLMs Everywhere: Running 70B models in browsers and iPhones using MLC — with Tianqi Chen of CMU / OctoML

10 Aug 2023 11 published claims 2 attributable people
Open original episode ↗ Read the evidence

Speakers in the public record

Shawn WangTianqi Chen

Claim mix

preference 3prediction 3evaluation 2commitment 2belief 1

Evidence policy

Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.

Claim ledger

The useful parts, with receipts.

11 published records

02 / preference

So I can tell you like what kind of I'm excited about. So, so I think that I have always been excited about this idea of continuous learning and lifelong learning in some sense.

“So I can tell you like what kind of I'm excited about. So, so I think that I have always been excited about this idea of continuous learning and lifelong learning in some sense.”
Speaker
Tianqi Chen
Publisher
Latent Space

03 / preference

I think making API better is certainly something useful, right? In general, one thing that we do try to push very hard on is this idea of easier universal deployment.

“I think making API better is certainly something useful, right? In general, one thing that we do try to push very hard on is this idea of easier universal deployment.”
Speaker
Tianqi Chen
Publisher
Latent Space

05 / evaluation

I don't remember specifics of them, but I think even nowadays, if you look at what people are using, tree-based models are still one of their toolkits.

“I don't remember specifics of them, but I think even nowadays, if you look at what people are using, tree-based models are still one of their toolkits.”
Speaker
Tianqi Chen
Publisher
Latent Space

07 / commitment

But I always want to come back to work on the deep learning field. So after XGBoost, I think I started to work with some folks on this particular MXNet.

“But I always want to come back to work on the deep learning field. So after XGBoost, I think I started to work with some folks on this particular MXNet.”
Speaker
Tianqi Chen
Publisher
Latent Space

08 / prediction

That we hope to elevate, yeah. And also, if you think about our future, definitely I feel like right now the technology, given the technology and the kind of hardware availability we have today, we will need to make use of all the possible hardware available out there.

“That we hope to elevate, yeah. And also, if you think about our future, definitely I feel like right now the technology, given the technology and the kind of hardware availability we have today, we will need to make use of all the possible hardware available out there.”
Speaker
Tianqi Chen
Publisher
Latent Space

09 / evaluation

Actually, on a single batch inference, more recently on CUDA, we get, I think, the most best performance you can get out there already on the 4-bit inference.

“Actually, on a single batch inference, more recently on CUDA, we get, I think, the most best performance you can get out there already on the 4-bit inference.”
Speaker
Tianqi Chen
Publisher
Latent Space

10 / preference

I would say that at some point, I'd love to talk about this comparison between extra boost or tree-based type AI or machine learning compared to deep learning, because I think there is a lot of interest around, I guess, merging the two disciplines, right?

“I would say that at some point, I'd love to talk about this comparison between extra boost or tree-based type AI or machine learning compared to deep learning, because I think there is a lot of interest around, I guess, merging the two disciplines, right?”
Speaker
Shawn Wang
Publisher
Latent Space
Search evidence