Google TPU, every mention
11 scenes · ← back to Google TPU
tap a year for its mentions
every year anyone Dylan Patel 12Bill Gurley 9Jensen Huang 3Clark Tang 1
Verbatim, from the transcripts: the passages where Google TPU comes up
The SpaceX IPO, Fable 5, AI Capex Update & Market Check w/ Gavin Baker, Andrew Fox & Clark Tang · Bg2 Pod
- ▶ 15:22 Clark Tang Um, you know, people always talk about Google and their ability to, to build a TPU and sell the TPU to Anthropic to generate revenues for AI.
NVIDIA: OpenAI, Future of Compute, and the American Dream | BG2 w/ Bill Gurley and Brad Gerstner · Bg2 Pod
- ▶ 45:38 Jensen Huang I mean, uh, TPU is on TPU seven. 3 times in the scene
Market Predictions, Rates & Inflation, DOGE, CES, AI Compute | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 1:13:23 Bill Gurley You've heard all of these hyperscalers talk about doing their own, um, processors of some sort, you know, both Tranium at Amazon and then the TPU at Google compete with NVIDIA, but they're buying NVIDIA's product.
AI Semiconductor Landscape feat. Dylan Patel | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 6:28 Dylan Patel So not everything internal is like, is, is, is Google, uh, is a GP, is a TPU, right?
- ▶ 14:16 Dylan Patel Like with Blackwell, not only is it way, way, way faster, anywhere from 10 to 15 times on really large models for inference, because they've optimized it for very large language models, they've also decided, hey, we're gonna cut our…
- ▶ 1:04:24 Dylan Patel Or accelerators like the TPU, Amazon Tranium, et cetera.
- ▶ 1:06:02 Dylan Patel Their whole thing at reInvent, if you really talk to them when they announced Trinium II and our whole post about it and our analysis of it is, like, supply chain-wise, this is, looks, you know, you squint your eyes, this looks like an… 2 times in the scene
- ▶ 1:10:36 Bill Gurley Let's go with the Google TPU. 7 times in the scene
- ▶ 1:13:32 Dylan Patel Um, and, and so number three is sort of Google is better off using all of their TPUs internally. 6 times in the scene
- ▶ 1:20:28 Dylan Patel like in the next six months, uh, there is a bit of a slowdown in Google TPU purchases because they have no data center space.
Ep20. AI Scaling Laws, DOGE, FSD 13, Trump Markets | BG2 w/ Bill Gurley & Brad Gerstner · Bg2 Pod
- ▶ 12:32 Bill Gurley You know, train a model on a big NVIDIA cluster, and you can run it on, you know, a different system, and there are certainly performance tests that are in the public that show the Groks and Cerebris and other TPUs, including the ones at…