CUDA, every mention
16 scenes · ← back to CUDA
tap a year for its mentions
every year anyone Matt Turck 27Viral Shah 2Todd Mostak 2Stephen Balaban 2Bryan Catanzaro 2Wes McKinney 1Richard Socher 1Dylan Patel 1David Luan 1Aravind Srinivas 1
Verbatim, from the transcripts: the passages where CUDA comes up
When AI Improves Itself | Richard Socher (Recursive)
- ▶ 1:08:54 Richard Socher Um, we also showed that they can build new CUDA kernels, which is very useful for faster inference.
Cerebras CEO: Why GPUs Can't Do Fast Inference
- ▶ 1:02 Matt Turck We started from what is a wafer and built up step by step, why GPUs struggle with fast inference, the three shortages nobody talks about, the decade in the desert when nobody wanted this chip, and why Andrew believes that CUDA is no longer…
- ▶ 1:01:11 Matt Turck Cuda as well. 5 times in the scene
Inside Nemotron & NVIDIA’s AI Lab | Bryan Catanzaro
- ▶ 18:07 Bryan Catanzaro Follows through over long time periods, you know, uh, and I've seen that with CUDA.
- ▶ 30:33 Bryan Catanzaro You know, we followed through over 10 plus years with CUDA, and we're doing that with Nemo Tron now.
The GPU Myth: State of AI Compute 2026 | Stephen Balaban
- ▶ 27:11 Stephen Balaban It's not just CUDA. 2 times in the scene
Dylan Patel: NVIDIA's New Moat & Why China is "Semiconductor Pilled”
- ▶ 10:07 Matt Turck And do you think, uh, CUDA is going to remain that mode? 15 times in the scene
- ▶ 39:10 Dylan Patel And now does that like weaken the CUDA moat?
Why This Ex-Meta Leader is Rethinking AI Infrastructure | Lin Qiao, CEO, Fireworks AI
- ▶ 44:29 Matt Turck Um, in particular, sort of the, the GPU layer and like the work you've done around CUDA. 3 times in the scene
Custom LLMs at Scale: Lamini CEO Sharon Zhou’s Playbook for Enterprise AI
- ▶ 34:45 Matt Turck Uh, accelerators are as powerful as NVIDIA CUDA. 3 times in the scene
Perplexity AI CEO on Dethroning Google & Redefining Search
- ▶ 48:47 Aravind Srinivas Like nobody else has any hardware that matches their, um, you know, the, the, the full package of efficiency and software supporting it in the form of CUDA or TensorRT and things like that.
Fireside Chat: Wes McKinney (Founder & CEO, Ursa Computing) with Matt Turck (Partner, FirstMark)
- ▶ 23:16 Wes McKinney So, you know, the folks from Nvidia, um, have a large team building the, the rapids project, which is, uh, uh, CUDA based, uh, uh, computing, uh, against arrow data.
A Fresh Approach to Technical Computing // Viral Shah & Stefan Karpinski, Julia Computing
- ▶ 12:14 Viral Shah Apart from CUDA and C, the toolkits that NVIDIA puts out, Julia is the only other, you know, widely used language that has native CUDA code gen. 2 times in the scene
The Power of GPU Analytics // Todd Mostak, MapD (FirstMark's Data Driven)
- ▶ 2:00 Todd Mostak Later, uh, NVIDIA developed CUDA, which was a general purpose programming language for GPUs, and people started porting all sorts of algorithms to GPUs.
- ▶ 20:51 Todd Mostak Probably first written in CUDA, but later maybe in Python, right on top of the database.
David Luan, Dextro // Real-World Video Understanding (FirstMark / Data Driven NYC)
- ▶ 17:43 David Luan But it's all of our, all of our, uh, everything we've built in-house in CUDA for NVIDIA GPUs.