Agam jain
@agam_jn
Co-founder at Tensorfuse (YC W24) l IIT Roorkee
Had a great time presenting @tensorfuse at the AI Tinkerers event! We deployed Stable Diffusion 3 model on AWS account using Tensorfuse in just 6 mins. Model was served via production ready API that autoscales wrt the traffic. The best part is that all of this was done from my…

"tensorkube volume create"
Shipping today: Tensorkube Volumes With a single command, you can now create and attach volumes to your deployments. Attaching volumes to your deployments helps you provide persistent storage, ensuring data longevity across pod restarts and deployments If you are building AI…
Update: We have moved to SF and this time without a return ticket After graduating from YC last year, even before writing the first line of code for Tensorfuse, we took a bold decision.. to operate in the US market from Day 0 coming from IITs, we already have a network in the…

We're filling up fast and only have ~20% of the seats remaining for our upcoming workshop in SF If you’re building AI apps, Voice Agents, LLM gateways, etc. with customised models, this workshop will help you: - Set up infra to fine-tune and deploy custom models directly in…
Customer Spotlight: How Vaero AI scaled to 1000s of custom LLMs with @tensorfuse ✅ 40% higher TPS, zero rate-limits ✅ 1000+ LoRA adapters deployed on a single GPU node ✅ 70% cost reduction by provisioning entire infra in their own AWS Full case study 👇
“My voice agent has high latency.” “My agent workers don’t scale properly.” “My LLM API bills are too high and function calling isn’t reliable.” @AWSstartups × @tensorfuse are teaming for a self hosted Finetuning & Inference workshop. 👉 Register now (link in comments)!
join us for the holy love of eks, genai and free food! lu.ma/mpzu7nkx
We're hosting a live, hands-on session focused on customising and serving open source LLMs in your own AWS cloud in partnership with @AWSstartups This is a builders only event where we will: - provision a completely serverless fine-tuning and inference infra in your own AWS…
We're cooking something big in partnership with @AWSstartups Will share more details by this week Stay tuned!

Who the heck came up with the idea of QR code menus at restaurants. It is super dumb Just ordering via menu is so so much easier and better
no longer unhealthy gpu nodes
Today we're launching a new feature. GPU Node Health Alerts. GPU nodes can sometimes go offline due to overheating or inference servers getting stuck in crash loops. Tensorfuse already tracks node health and auto-removes unhealthy nodes. Now, we’ve added email alerts if nodes…
WTH is happening with Aviation Industry! Yesterday: Japan Airlines Flight Plunges 26,000 Feet mid air June 12th: Worst ever crash of Air India flight 2 days later: Another AI flight dropped 900 feet shortly after departure Days later: Another AI flight made an emergency…
My co-founder @samagra_sharma is live blogging our progress on the Voice AI blog! - 10% spelling mistakes - 30% grammar errors - 100% nerd content on inference servers Tune in now: samagra.me/philosophy/202…

We're self hosting the entire Voice AI Stack and will open source all the code! It's much harder than we thought! Lot of devs have shared this issue and so we're planning a comprehensive blog on how to self-host the complete Voice AI agent stack using SOTA open-source models…
SSH Isn't Enough: Why Production-Grade AI Deployment Demands More! Running a model by SSHing into a remote server and executing scripts is not production deployment. It will probably work fine for initial 5-10 customers. But if you care about: ✅ Uptime, ✅ Reliability,…

AI agents ftw!
🤖 Your AI agents just got better, faster and cost effective. With our latest integration with @crewAIInc , a popular open source AI agent framework, you can now build AI agents with self hosted models in your own AWS. Follow the full tutorial below and join our slack community…
if you're applying for 1-10th position at an early stage startup and you've no clue about ESOPs or equity and neither do you want to learn about them .. big red flag!
We're a small team of 4 engineers building the future of AI inference. We're based out of San Francisco and Bengaluru. As we wake up to the situation of a potential war, it is quite tense and distracting especially when one of our team member's family is near the affected area.…

Recently, one of our users were fine-tuning LoRA adapters via Axolotl. They ran into an issue where some occasional training jobs would run extremely slowly and eventually crash with a “Watchdog timeout” error. So we dig deep into the Nvidia NCCL rabbit hole, fixed the…

when you truly want to learn, there is no goal! the only purpose of learning, if at all theres any is to satisfy our never ending curiosity. That’s not to say there is no method to it, of course there is .. but Method != Goal