Baseten

We’re thrilled to announce that we have raised $300M at a $5B valuation. The round is led by IVP and CapitalG, both doubling down on their investment in Baseten, and joined by 01A, Altimeter, Battery Ventures, BOND, BoxGroup, Blackbird Ventures, Conviction, Greylock, and NVIDIA. Read more here: baseten.co/blog/announcin…

Special thanks to @maxricodecastro for designing the beautiful website! And huge thanks to @alanaagoyal ,@amiruci, and @baseten team for providing us the inference engine to deploy the model bioreason.net

📗

I love throwing parties 🤍

Inference engineering is having its moment.. glad to be around for it. 💚💚💚

@rapprach truly a generational team

@baseten we have the best infra team, hands down

Cold starts for large models are one of the hardest problems in AI inference infrastructure. Today we're launching the Baseten Delivery Network (BDN) to solve one of the hardest parts of this problem. 2–3x faster cold starts for large models at scale via optimizations at the pod, node, and cluster levels.

Developers used to argue about programming languages; now they argue about harnesses. NemoClaw is NVIDIA's answer to your OpenClaw safety woes — zero permissions by default, sandboxed subagents, private inference enforced at the infra layer. Here's a guide on how to start:

Lets go! Got my signed copy from Philip!

Want to enjoy a sweet treat in between sessions and meetings? Come by for a scoop of our ice cream, created exclusively with @humphryslocombe 🍦

If you've signed up for a physical copy of Inference Engineering and are at GTC, come to our booth for a free copy fresh off the press! Our author @philipkiely will be there from 12–1 PM and 3–5 PM today. First come first serve. Booth #931

Present and future inference engineers at NVIDIA GTC.

Travel in style. Get rides to and from GTC in our cars. 👀

We are very excited to reveal the workshops at our upcoming Media Entertainment hackathon from teams shipping video AI in production: ✅ @twelve_labs: Scalable retrieval and temporal reasoning only our Marengo + Pegasus models can handle ✅ @awscloud and @TrackItCloud: Bedrock deployment patterns and media workload optimization on AWS infrastructure ✅ @baseten: Model serving with production latency ✅ @LTXStudio: Video generation meets understanding ✅ @nvidia: GPU architecture for video inference These are technical deep-dives, so expect benchmarks and diagrams - not pitches. All participants get sponsor credits + platform access + engineer support. March 28-29 | Los Angeles Applications close March 25 luma.com/0kcl7lcj

Great conversations on AI, agents, and evals at the @braintrust x @modal x @browserbase x @Zai_org agents after hours in San Jose this evening. Hosting another happy hour with @awscloud and @baseten tmrw. Come through.

WAIT!!! ALL THIS WAS JUST LAST WEEK IN TECH???

Day one at NVIDIA GTC complete! Books are flying off the shelves, restocked today for expo open at booth 931.

@cwkdotone 😇🙏

Can confirm that @baseten is in fact based.

Giving away signed copies of Inference Engineering at NVIDIA GTC — stop by booth 931!