Baseten, every mention
23 scenes · ← back to Baseten
tap a year for its mentions
every year anyone Shawn Wang 11Alessio Fanelli 2Stephanie Palazzolo 1Philip Kiely 1Loïc Houssier 1
Verbatim, from the transcripts: the passages where Baseten comes up
Next 100x in AI: Inference, Networking, & Self-Optimizing Models — Philip Kiely & Ali Taha, Baseten
- ▶ 1:28 Shawn Wang Okay, we're here in the studio with, uh, Philip, uh, old friend from, from, uh, Inference Engineering, the book, as well as Base 10 and, uh, everything that you've done, you and I have done before, as well as Ali, welcome. 2 times in the scene
- ▶ 2:37 Alessio Fanelli What happens when I send a long query, say, 200,000 tokens into base tens inference? 2 times in the scene
- ▶ 4:43 Shawn Wang Yeah, I mean, one of the key differentiators when I was talking with Basen initially was that actually people who want very, very high volume just need to rent by the box, because then it's up to you to figure out how to saturate the box.
- ▶ 12:53 Shawn Wang Ok, so, like, you know, a lot of people, all you guys, right, whenever a new model launch, like, people rush to say, like, oh, Hugging Face supports this, Fireworks supports this, Base 10 supports this, and I'm like, yeah, of course you… 2 times in the scene
- ▶ 51:54 Philip Kiely Yeah, uh, shout out, shout out to Luke from Basetent's design team for making these, these beautiful images.
- ▶ 1:29:07 Shawn Wang That's the job of, of phase 10.
- ▶ 1:41:44 Shawn Wang Yeah, uh, highest ROI thing in the history of Base 10, right?
The Future of AI Infra: from Kubernetes to Agent Sandboxes — Akshat Bubna, Modal CTO
The Future of Email: Superhuman CTO on Your Inbox As the Real AI Agent (Not ChatGPT) — Loïc Houssier
- ▶ 30:12 Loïc Houssier Uh, but, uh, we use Base-Ten to run some, uh, I would say some LAMA, some BERT model for classification.
- ▶ 32:50 Shawn Wang Interesting question on base 10. 4 times in the scene
The AI Agenda: GPT5 leaks and the business of AI News — Steph Palazzolo, The Information
- ▶ 8:34 Stephanie Palazzolo You mentioned some of them, Fireworks, Modal, there's Together, there's Base 10.
DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)
- ▶ 0:30 unnamed speaker And Yining Zhang from Base 10. 3 times in the scene
- ▶ 2:09 unnamed speaker And that's obviously beneficial for Base-Ten.
- ▶ 4:17 unnamed speaker Can you maybe just give people a quick rundown of all the models you support on base then how it compares just on size, just to, you know, people here, 671 gigabytes. 2 times in the scene
- ▶ 8:43 unnamed speaker I'll let Yeneng answer the, the, the sort of patterns around, you know, uh, using FPA in training, but I want to draw one, one distinction that, that I think gets to the, the latter part of your question, Sean, which is that unlike… 2 times in the scene
- ▶ 20:36 unnamed speaker We have customers on, on based end that are using TensorFlow and we have ones that are using VL and we have a growing number that are using SGLang too.
- ▶ 22:40 unnamed speaker Another place where, where we didn't think about at first, but became important was seeing more and more use cases where the customer was saying, I can serve my models on base 10 using trust fine, but my use case is not just call the… 4 times in the scene
- ▶ 24:48 unnamed speaker Everything just goes through the baseline platform the same. 4 times in the scene
- ▶ 31:08 unnamed speaker So, you know, there are models on base end today that have 50 replicas in GCP East and, uh, 80 replicas in, in, uh, AWS West and, and Oracle in, in London, um, et cetera.
- ▶ 36:30 unnamed speaker And for your case specifically, how does that change when you have like a base 10 type use case where you don't, do not have a shared endpoint versus like, you know, is this less helpful for GPU clouds to do one model for like many people…
- ▶ 42:12 unnamed speaker We can talk about, uh, the last one, I, which I don't know if it's as relevant for base 10, which is the third technique of SG language is API speculative execution, which seems to be only for API only models.
- ▶ 54:51 unnamed speaker Maybe even separate, put it on a separate property than base 10 and just go like, here's what we think, you know, mission critical a application should be and, you know, have some thought leadership there and, and flesh it out 3 times in the scene