High Signal Podcasts Evidence ledger
Method
Browse
← Back to evidence

Evidence receipt / evaluation

Published · transcript-backed

Tri Dao: evaluation

26 Jul 2023 Latent Space FlashAttention 2: making Transformers 800% faster w/o approximation - with Tri Dao of Together AI

“By the end, I just ended up working with the code a whole lot more and I realized that, hey, there are these inefficiencies still in Flash Attention.”

— Tri Dao

Source trail

Everything needed to verify it.

Speaker
Tri Dao
Attribution
Verified speaker
Claim type
evaluation
Recorded
26 Jul 2023
Publisher
Latent Space

Transcript context

…I like that your work has been focused on not making benchmarks better, but it's like, let's just make everything faster. So it's very horizontal. So FlashAttention 2, you just released that on Monday. I read in the blog post that a lot of the work was also related to some of the NVIDIA library updates. Yeah, maybe run us through some of those changes and some of the innovations there. Yeah, for sure. So FlashAttention 2 is something I've been working on for the past couple of months. So the story is the NVIDIA CUTLASS team, they released a new version of their library, which contains all these primitives to allow you to do matrix multiply or memory loading on GPU efficiently. So it's a great library and I built on that. So they released their version 3 back in January and I got really excited and I wanted to play with that library. So as an excuse, I was just like, okay, I'm going to refactor my code and use this library. So that was kind of the start of the project. By the end, I just ended up working with the code a whole lot more and I realized that, hey, there are these inefficiencies still in Flash Attention. We could change this way or that way and make it, in the end, twice as fast. But of course, building on the library that the NVIDIA folks released. So that was kind of a really fun exercise. I was starting out, it's just an excuse for myself to play with the new library. What ended up was several months of improvement, improving Flash Attention, discovering new ideas. And in the end, we managed to make it 2x faster and now it's pretty close to probably the efficiency of things like matrix multiply, which is probably the most optimized subroutine on the planet. So we're really happy about it. The NVIDIA Cutlass team has been very supportive and hopefully in the future, we're going to collaborate more. And since it's an NVIDIA library, can you only run this on CUDA runtimes? Or could you use this and then run it on an AMD GPU?…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.

Search evidence