Ro Arepally

I am a person

[Ro Arepally @rarepally]

@bernhardsson True

[Ro Arepally @rarepally]

Since we're not reading the code anyway, let's just write everything in Haskell.

[Ro Arepally @rarepally]

A premium commercial for a premium product!

[Modal @modal]

Unstick your AI

Modal x @krazamtv

[Ro Arepally @rarepally]

@peywalt 🤣

[Ro Arepally @rarepally]

Insightful thread by an insightful person!

[Jonathon Belotti @jonobelotti_IO]

GPUs are unreliable at scale.

At @modal we've scaled to 20,000+ concurrent GPUs across AWS, GCP, Azure, and OCI, with 1M+ instances launched. Public-cloud GPUs fail in many ways, and we’ve seen most of them.

Here’s how we handle GPU reliability 👇

[Ro Arepally @rarepally]

Absolutely huge

[Akshat Bubna @akshat_b]

Two days since DFlash was released, and @_dcw02 (on @modal research) already shipped support for it in SGLang.

Why are we so excited about this?

Diffusion speculators let us get *way* higher tok/s than auto-regressive models. E.g. we're seeing a 4.73x boost with H200s + FA3 already — with still more improvements to come!

Reach out to us if we can help you get this in prod today, and huge thanks to @zhijianliu_ and team for coming up with this technique.

[Akshat Bubna @akshat_b]

Two days since DFlash was released, and @_dcw02 (on @modal research) already shipped support for it in SGLang.

Why are we so excited about this?

Diffusion speculators let us get *way* higher tok/s than auto-regressive models. E.g. we're seeing a 4.73x boost with H200s + FA3 already — with still more improvements to come!

Reach out to us if we can help you get this in prod today, and huge thanks to @zhijianliu_ and team for coming up with this technique.

[Modal @modal]

We've moved – a peek into our new NYC HQ 🗽

[Ro Arepally @rarepally]

Divya is incredibly smart and has great taste and judgement. Congrats and excited to see where this goes!

[Divya Gupta @divyahansg]

Founding Beacon with @nilamg has been the most intense but also fulfilling time of my life. In just a year, we’ve grown to a team of 30+ and acquired dozens of mission-critical software businesses that quietly power everyday life, helping them bring AI to real-world industries.

We are deeply thankful to the entrepreneurs who have entrusted us with their life’s work and our partners at General Catalyst, Lightspeed, D1 Capital, MSD & BDT, and Sator Grove, along with our angels and advisors.

This $250M Series B fundraise enables us to increase the scale of our ambitions to build a generational AI holding company.

We are hiring across many roles! Check out our careers page.

[Divya Gupta @divyahansg]

Founding Beacon with @nilamg has been the most intense but also fulfilling time of my life. In just a year, we’ve grown to a team of 30+ and acquired dozens of mission-critical software businesses that quietly power everyday life, helping them bring AI to real-world industries.

We are deeply thankful to the entrepreneurs who have entrusted us with their life’s work and our partners at General Catalyst, Lightspeed, D1 Capital, MSD & BDT, and Sator Grove, along with our angels and advisors.

This $250M Series B fundraise enables us to increase the scale of our ambitions to build a generational AI holding company.

We are hiring across many roles! Check out our careers page.

[Adithya S K @adithya_s_k]

Write deep learning code on your laptop and run it instantly on GPUs - that's every developer/reseachers dream

@thinkymachines offers this with Thinker

You can do something similar by just using @modal right now !!

I’ve written a blog + hands-on tutorial breaking down how you can train, fine-tune, and deploy LLMs/VLMs on GPUs in scalable manner without worrying much about infra

[Erik Bernhardsson @bernhardsson]

It's true – @modal has raised a $87M Series B at a $1.1B valuation to advance the future of AI infrastructure. 

Thank you to @Lux_Capital, @Redpoint, @AmplifyPartners, and others.

Now more than ever, AI demands a complete reinvention of traditional compute infrastructure

[Charles 🎉 Frye @charles_irl]

come try our gay notebooks

https://t.co/RMZJTD9dJt

[Ro Arepally @rarepally]

@bernhardsson @charles_irl 🤣

[Ro Arepally @rarepally]

🤩 love an easy way to experiment with GPUs

[Eric Zhang @ekzhang1]

We're thrilled to share Modal Notebooks: a new, powerful cloud-hosted GPU notebook. It has modern real-time collaborative editing and is backed by our AI infrastructure — swap GPUs in seconds.

Modal Notebooks are generally available, and you can start using them now. 🧵

[Ro Arepally @rarepally]

@charles_irl @modal So dope

[Charles 🎉 Frye @charles_irl]

I like making GPUs go brrt at @modal.

I wrote up what I've learned along the way in an extension to the GPU Glossary -- our "CUDA Docs for Humans".

Introducing: the GPU 𝔓𝔢𝔯𝔣𝔬𝔯𝔪𝔞𝔫𝔠𝔢 Glossary.

https://t.co/9IDfgGqVFX

[Erik Bernhardsson @bernhardsson]

Querying Billions of GitHub Events Using Modal and DuckDB

https://t.co/a0b7L2Wky4

Very cool demo of how to use Modal for fan-out parallelism

[Akshat Bubna @akshat_b]

At @modal we've built every layer of the AI infra stack from scratch — from filesystems and networking to our own async queues and multi-cloud GPU orchestration.

I sat down with @narayanarjun from @amplifypartners to go into depth on all of this, including the fun ways the Linux kernel has tried to stop us along the way:

[Ro Arepally @rarepally]

An engineer's technical abilities are highly correlated with how often they use the word "perhaps".