TensorFuse (YC W24)

Multimodal llm on your Amazon Web Services (AWS)

Tensorfuse now supports creating deployments with a config file ?? In Tensorfuse, apps are deployed using the tensorkube deploy command. This command provides many options to deploy your apps, such as defining min and max scale, types of GPU, CPU memory, etc. If you want to use the same set of options for multiple deployments, or keep the options in a file for future reference, you can use a config file to declare the flags and use it to run tensorkube deploy. Watch the demo to see how you can work with Config Files in Tensorfuse ************ Deploy your first GenAI app, on your own cloud, in minutes. Get started with our docs. Link is in the comments!

If you are a company doing enterprise / on-prem deployments, always ask your customers to create a separate cloud Sub-Account for your specific app. If possible get access to that account's Cloudtrail logs. This ensures that no one messes with your environment. Also, include in your legal SLAs that any modifications from them will essentially breach the SLA and you won't be held liable. Here is a basic template that we follow with our customers: https://lnkd.in/gZXk_VtT

When we started TensorFuse (YC W24), most of our customers were image and audio companies. Open-source LLMs were far from production-ready. The trend has changed in the past two months. QLoRA/LoRA + Axolotl + Tensorfuse LoRA swapping has paved the way. Super bullish on OS LLMs.

Sometimes I feel so lucky to have the opportunity to build something like TensorFuse (YC W24). Being at the frontiers of two great technologies - the cloud and the AI (two of the last three waves if you count crypto) feels like a rollercoaster. One side gives you endless explanations (ML), the other, just manpages. It’s liberating! I handle containers, humanity handles the rest.

TensorFuse (YC W24) now supports working with Secrets. Deployments often require sensitive information such as passwords, API keys, and access tokens. Hardcoding these in the code is not secure. With Tensorfuse Secrets, you can securely store and use such sensitive data in your code. Watch the demo to see how you can work with Secrets in Tensorfuse. _________ Deploy your first GenAI app on your own cloud in minutes. Check out our docs to get started—the link is in the comments!

Check out the demo of Tensorfuse dev containers at the SF Awesome AI Dev Tools Meetup

We recently helped a YC company launch production @tensorfuse by speeding up their GPU deployments. Thanks for the love Albert!

You can now run popular image models using ComfyUI on your AWS account using Tensorfuse ?? ComfyUI lets you design and execute advanced stable diffusion pipelines using a graph/flowchart based interface. You can use any model for deployment as given in?examples for ComfyUI?through Tensorfuse. Get started today with our guide that includes all the code and env files: https://lnkd.in/gzahdz5s

We will be launching our startup deal soon! At TensorFuse (YC W24), we've helped multiple fast growing startups cut time to market of their AI app by ~3 weeks. Here's what our our customers have to say about us: - With Tensorfuse, I can rapidly deploy models within our own environment has greatly accelerated development while cutting costs - The Tensorfuse team and product has been great for us. It helped us remove a ton of our own patched together DevOps and free up an engineer. - The team has gone above and beyond onboarding us and supporting us, at all hours of the day. Super easy to set up, would recommend. and many more... If you're a startup and want to deploy models on your own cloud, leveraging your credits, we've got you covered. We'll be announcing the deal on Monday, you can directly apply and check if you're eligible!