2025 is the year of inference. We're thrilled to announce our $75m Series C co-led by IVP and Spark Capital with participation from Greylock, Conviction, basecase capital, South Park Commons and Lachy Groom. We're also excited to add Dick Costolo and Adam Bain from 01 Advisors as new investors. Check out our CEO Tuhin's blog to learn more. It's time to build!
关于我们
At Baseten we provide all the infrastructure you need to deploy and serve ML models performantly, scalably, and cost-efficiently. Get started in minutes, and avoid getting tangled in complex deployment processes. You can deploy best-in-class open-source models and take advantage of optimized serving for your own models. We also utilize horizontally scalable services that take you from prototype to production, with light-speed inference on infra that autoscales with your traffic. Best in class doesn't mean breaking the bank. Run your models on the best infrastructure without running up costs by taking advantage of our scaled-to-zero feature.
- 网站
-
https://www.baseten.co/
Baseten的外部链接
- 所属行业
- 软件开发
- 规模
- 51-200 人
- 总部
- San Francisco，CA
- 类型
- 私人持股
- 领域
- developer tools和software engineering
产品
![点击此处查看Baseten]()
Baseten
机器学习软件
At Baseten we provide all the infrastructure you need to deploy and serve ML models performantly, scalably, and cost-efficiently. Get started in minutes, and avoid getting tangled in complex deployment processes. You can deploy best-in-class open-source models and take advantage of optimized serving for your own models. We also utilize horizontally scalable services that take you from prototype to production, with light-speed inference on infra that autoscales with your traffic. Best in class doesn't mean breaking the bank. Run your models on the best infrastructure without running up costs by taking advantage of our scaled-to-zero feature.
地点
Baseten员工
动态
-
Baseten转发了
I'm speaking twice at GTC! Mark your calendars for 10 AM on Wednesday, March 19 for "Advanced Techniques for Inference Optimization With TensorRT-LLM" with Baseten co-founder Pankaj Gupta. And when you're in the expo hall on Tuesday the 18th, swing by the Lightning Theater at 3PM for "Field Notes on Scaling Real-Time AI-Native Applications in Production" https://lnkd.in/gcnCpfra
-
Gemma 3 just dropped from Google ?? If you want to try it out, you can deploy it in two clicks from our model library. Gemma 3 introduces: ? Multimodality (vision-language input) ? Longer context windows (up to 128k tokens) ? LMArena ELO comparable to 20x bigger models ? Improved math, reasoning, and chat capabilities ?? Try it here: https://lnkd.in/ebrPd2Jq
-
If you're at HumanX right now, Philip Kiely and Andy Taylor are ready for you at booth #701. Come say hi, see a demo, and grab some swag!
-
-
Meet the Baseten crew at HumanX! We're in Las Vegas and ready for a great week. Visit us at booth #701 and chat with Tuhin Srivastava, Philip Kiely, Mike Bilodeau, and Andy Taylor, get a demo, and grab some swag!
-
-
Can the new open-source Qwen QwQ-32B model compete with other SOTA multi-hundred-billion-parameter models? You tell us. You can start using QwQ-32B from our model library in two clicks. We currently have it running at 90 tokens per second on a single H100 using a new speculative decoding stack—around 2x more than the rest of the leaderboard on Artificial Analysis. Try it out: https://lnkd.in/efDA4MiH
-
We're celebrating our first podcast episode by streaming it live! Join Senior Engineers Marius Killinger and Tyron Jung along with our host Rachel Rapp to learn about all things compound AI this Thursday, March 6th at 11 a.m. PT. You'll learn how compound AI is changing the AI landscape, what makes it difficult to serve in production, how to build ultra-performant compound AI systems, and much more. Register here: https://lnkd.in/dW_YqmKJ
-
-
"We want to work with our customers. We enjoy working with our customers. The thing you will hear time and time again is 'these people felt like an extension of my team.'" Thanks Craig S. Smith for having Tuhin Srivastava on the Eye On A.I. podcast! Tuhin breaks down everything from the hidden costs of inference to the shift from closed-source to open-source models and our core pillars of inference. ?? Check out the full episode here: https://lnkd.in/gTV4fwTk
-
Better model efficiency is leading to increased AI adoption, especially in the enterprise. Deirdre Bosa and the team at CNBC synced with Baseten CEO Tuhin Srivastava on exactly this topic. We optimize for our customers' success, prioritizing both model performance and cost efficiency. As a result, we've seen outcomes like 60% reduced spend for AI workloads, leading to 2x AI adoption. Check out the full clip on CNBC for more details on how open-source models and model efficiency are impacting the landscape: https://lnkd.in/eTRi8BsH
-