What does @modal do? How does it work? What's different about AI infra? Why did we throw out Kubernetes and Docker built our own infra stack from scratch?
@AmplifyPartners wrote this article about a lot of the gory details under the hood of Modal – link in 🧵
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…
New tutorial on Fine-tuning Whisper 🎙️
Open-source ASR models are having a ~moment~
You can fine-tune them to achieve higher accuracy on things like domain-specific vocab.
Proud to announce that @modal_labs was a Day 0 Lunch Partner for the release of gpt-oss.
That is, on Day 0 I got lunch with @mgoin_ of @vllm_project and then had him look at my and @shariqmobin's code to deploy the model on Modal.
Proud to announce that @modal_labs was a Day 0 Lunch Partner for the release of gpt-oss.
That is, on Day 0 I got lunch with @mgoin_ of @vllm_project and then had him look at my and @shariqmobin's code to deploy the model on Modal. https://t.co/BCLmrRfq7v
Lots of new frontier models this week. So this Sunday, we’re hosting the Applied AI Hackathon in SF to push the limits of what’s possible.
$100,000 in prizes. Judges including @karpathy and @swyx.
12 hours to build something that shouldn’t exist yet.
Details & how to join👇
a woman at the checkout counter told me she liked my hair because it was "a great use of my free will"
little does she know that i am actually obligated to maintain this style so that people will recognize me from the Internet
For whatever reason, @modal_labs always gets compared to "inference providers", which always confuses me?
Modal was always built to be a general-purpose platform for AI/ML/data. Yes – we do inference really well! But we also do batch processing, sandboxes, training, ...
My new job is to get everyone else to see what I see in Modal:
the future of data-driven computing
powered by open generative models trained at the scale of the web
and adapted to end-user needs by code, customization, and continual improvement.
LFG.
modal.com
You can now cold-start vLLM in 5s on @modal_labs.
GPU snapshotting is a primitive that unlocks a whole world of possibilities we're only beginning to unlock.
If you're interested in working on the frontiers of what's possible with AI infra, please reach out :)
You can now cold-start vLLM in 5s on @modal_labs.
GPU snapshotting is a primitive that unlocks a whole world of possibilities we're only beginning to unlock.
If you're interested in working on the frontiers of what's possible with AI infra, please reach out :)
I’m soo psyched to announce this one. We have raised again!
Raised the bar for AI inference. By snapshotting GPU memory, we can cold start containers running vLLM or many other things extremely fast. This will be a game changer for many customers.
I’m soo psyched to announce this one. We have raised again!
Raised the bar for AI inference. By snapshotting GPU memory, we can cold start containers running vLLM or many other things extremely fast. This will be a game changer for many customers.
We just launched GPU memory snapshotting on @modal_labs in alpha. Speed up cold boots by up to 12x 😇
If you're deploying AI models, a huge amount of cold boot time comes from loading model weights into GPU memory. This makes it difficult to scale GPU resources up and down…
1K Followers 2K FollowingInterested in making LLMs go brrrrr
x+1: MS @LTIatCMU
x: LLM @Zomato
x-N: https://t.co/ht5ObQh7RV & Program Synthesis with LLMs @ProseMsft
2K Followers 2K Followingmath and poetry. ex @lyft, @bloomberg, now changing healthcare with the power of my voice. DM if you want to make a new friend.
2K Followers 2K FollowingOpen-source pipeline framework that integrates all your ML tools. Get all your ML workflows running on any tooling stack with minimum effort.
23K Followers 110 FollowingMathematician, @UCBerkeley professor, author of LOVE & MATH (published in 20 languages), host of AfterMath series on YouTube, music expolorer as DJ Moonstein
9K Followers 1K FollowingA research group in @StanfordAILab working on the foundations of machine learning & systems. https://t.co/JHK58TDorG Ostensibly supervised by Chris Ré
554K Followers 131 FollowingFather of three, Creator of Ruby on Rails + Omarchy, Co-owner & CTO of 37signals, Shopify director, NYT best-selling author, and Le Mans 24h class-winner.
64K Followers 1K FollowingCo-founder and CTO at @huggingface 🤗. ML/AI for everyone, building products to propel communities fwd. @Stanford + @Polytechnique
1K Followers 2K FollowingInterested in making LLMs go brrrrr
x+1: MS @LTIatCMU
x: LLM @Zomato
x-N: https://t.co/ht5ObQh7RV & Program Synthesis with LLMs @ProseMsft
3K Followers 1K FollowingCo-Founder at @Phonic_Co. Previously @Stanford CS PhD Dropout, @MosaicML, CS @MIT. I tend to be wrong, but the learning process makes it enjoyable. 🇵🇰🇺🇲
6K Followers 131 FollowingMachine pedagogue and data aesthete. Creator of https://t.co/imXawO1Iwk. Currently @modal_labs, building a new way to develop in the cloud.