Tri Dao
6 statements across 2 episodes · 5 bullish · 0 bearish · 2 people on the record · first statement Aug 3, 2023 by Tri Dao · said 16 times in 12 episodes since 2023 · across every show →
On the record as a speaker too: Tri Dao's record, appearances and statements → this page counts the times other people say the name.
Mentions by year
brought up most by Alessio Fanelli (6), Ali Taha (2), Quentin Anthony (1), Diego Bachman (1), Chris Lattner (1)
tap a year for its mentions
2026 2 mentions in 1 episode
2025 5 mentions in 5 episodes 1 per episode
- How Zyphra went all-in on AMD + Why Devs feel faster with AI but are slower — with Quentin Anthony
- Building Jamba 3B: the tiny Hybrid Transformer State Space Reasoning Model - Barak Lenz, CTO of AI21
- ⚡️ Beyond Transformers with Power Retention
- The Shape of Compute (Chris Lattner of Modular)
- 2024 Year in Review: The Big Scaling Debate, the Four Wars of AI, Top Themes and the Rise of Agents
- every mention in 2025, scene by scene →
2024 7 mentions in 5 episodes 1 per episode
- The Winds of AI Winter (Q2 Four Wars of the AI Stack Recap)
- Building an open AI company - with Ce and Vipul of Together AI
- Language Agents: From Reasoning to Acting — with Shunyu Yao of OpenAI, Harrison Chase of LangGraph
- Answer.ai & AI Magic with Jeremy Howard
- The Origin and Future of RLHF: the secret ingredient for ChatGPT - with Nathan Lambert
- every mention in 2024, scene by scene →
2023 2 mentions in 1 episode
Everything said about Tri Dao, oldest first
Aug 3, 2023 positive
Aug 3, 2023 positive
Aug 3, 2023 neutral
SRAM capacity will stagnate, making memory-aware algorithms vital
“And so, yeah, I think in the future SRAM probably won't get that much larger because you don't have that much area. HRAM will get larger and faster, and so I think it becomes more important to design algorithms that take advantage of this memory asymmetry.”
Aug 3, 2023 positive
FlashAttention achieves 2x to 4x wall-clock speedup with linear memory
“So in the end, we ended up being, the memory is linear in sequence length. In terms of computation, it's still quadratic, but we managed to make it much more hardware friendly, and as a result, we do get wall clock speed up on the order of two to four X which …”
Aug 3, 2023 positive
Releasing highly optimized code mattered more than the FlashAttention paper
“I think when we were writing the paper, I remember sending an email to one of my advisors, like hey, I'm excited about this paper but I think the most important thing will be the artifact, which is the code. So I knew that, like, the code will be valuable and,…”
Jun 13, 2025 positive
Modular's Mojo FlashAttention beats Tri Dao's reference implementation
“We're beating the tree DAO reference implementation that everybody uses, for example, right? Written fully in Mojo. Again, all of our, GPU kernels are written in Mojo. You can go see the history of the team building this, and it was done in just a few weeks, r…”