
Tensorfuse
Tensorfuse is a YC Winter 2024 (W24) company. Team of 2.
About Tensorfuse
Summary
Tensorfuse deploys and autoscales GPU containers for AI inference inside a company's own AWS account, replacing the need to manually configure and manage production inference infrastructure. Engineering teams bring a Dockerfile and GPU capacity; Tensorfuse handles deployment, scaling, and orchestration across frameworks such as vLLM, TensorRT, and Dynamo. The target customer is any B2B team running AI models at scale who wants to keep workloads in their own cloud rather than a third-party GPU service.
Go-to-market
B2B software teams self-provision by connecting their existing AWS account, with the product promising a production-ready setup in under 60 minutes.
From the Y Combinator listing
Run serverless GPUs on your own cloud
Tensorfuse helps you run fast, scalable AI inference in your own AWS account. Run any model, use any inference server (vLLM, TensorRT, Dynamo) and get ready to scale your AI inference to 1000s of users - all set up in under 60 mins Just bring: 1. Your code and env as Dockerfile 2. Your AWS account with GPU capacity We handle the rest—deploying, managing, and autoscaling your GPU containers on production-grade infrastructure.
Facts
- B2B / B2B -> Engineering, Product and Design
- 2
- Active
- Early
Founders (2)
Score every batch against your own thesis
GPAgent's sourcing agent reads every company in a batch, scores each one against your fund's thesis in a private workspace, and lines up the founders worth meeting before Demo Day. You decide who to contact. Your scores, notes, and pipeline never appear on these pages.
How Accelerator intelligence works