Modal

1.5K posts

Modal banner
Modal

Modal

@modal

AI infrastructure that developers love 💚 Run inference, sandboxes, batch processing, training, and many other things on Modal

New York City Katılım Temmuz 2022
142 Takip Edilen29.4K Takipçiler
Modal retweetledi
Charles 🎉 Frye
Charles 🎉 Frye@charles_irl·
Step 4 to achieve truly serverless GPUs for AI inference: skip over unserializable inference engine setup steps like CUDA graph capture and Torch compilation by stacking GPU snapshots and CPU snapshots.
English
3
11
106
8.4K
Joe Weisenthal
Joe Weisenthal@TheStalwart·
What is the best argument for the "compute" market will evolve in such a way that there will be an actively traded market for capacity, rather than just long-term bilateral contracts between inference providers and GPU owners? (Assuming those remain distinct categories)
English
39
3
86
19.5K
Lamitr Dhir
Lamitr Dhir@LamitrD·
@modal who do we talk to for startup credits (please)
English
1
0
0
36
Akshat Bubna
Akshat Bubna@akshat_b·
Fun fact: @ScottWu46 (while younger than me) was my first manager over a decade ago. While he is definitively the smartest person I've ever met, the piece really undersells how great Scott is as a human. And how much he loves sushi.
Akshat Bubna tweet media
Colossus@colossusmag

Scott Wu is the co-founder of Cognition AI, one of the fastest-growing companies in history. He’s also the greatest competitive programmer the US has ever produced. You may have seen him doing impossible card tricks and mental math. You’ve never seen him asked about weed, Michael Jordan, cancer, and human consciousness over a punnet of strawberries. That is what Colossus editor-in-chief Jeremy Stern did on a recent visit to San Francisco. For those less familiar with @ScottWu46: In 2nd grade, he entered a math competition for 7th graders, lost, and was so furious he still fumes about it 20 years later. The next year he entered the 9th-grade division as a 3rd-grader and got a perfect score. Then he won first place at the US national middle-school math competition and three straight gold medals at the International Olympiad in Informatics, where he became the greatest American gold-medalist and coach in history. Most of the people running the biggest AI companies met as teenagers, competing for their countries on international math and science teams. OpenAI’s Greg Brockman, Anthropic’s Dario Amodei, Meta’s Alexandr Wang, to name just a few. Most agree that the von Neumann among them was Scott Wu. In November 2023, a few weeks after his mother died of lung cancer, on the day Sam Altman was fired from OpenAI, Wu founded his own AI company: Cognition. He was 26 and saw earlier than almost anyone that AI would converge on agents that work in the background, 24/7, like coworkers. He shipped Cognition’s AI software engineer Devin in March 2024. It worked poorly, and he took intense public criticism for it. Now, in its first 18 months of service, Devin has generated $445 million of revenue run rate and usage has doubled every eight weeks. The US Army, Goldman Sachs, and Mercedes-Benz are all customers. Cognition is raising at a valuation around $25 billion. @JeremySternLA sat down with Wu, the emperor of the nerds, to ask the questions we’d all ask one of the smartest people in America—building the most consequential technology of our generation—if we ever got the chance. As well as MJ and weed, they talk about the cluster of competitive math prodigies behind so much of AI, what makes us human when AGI arrives, and why Wu believes he was put on this earth to teach AI how to code. Read the piece below.

English
13
10
711
116.2K
Modal retweetledi
Akshat Shrivastava
Akshat Shrivastava@AkshatS07·
All inference running on @modal . Mk1 introduced new inference requirements for us — native video at 2 FPS increases prompt length, structured outputs and hybrid thinking increase decode length. Modal was the right partner to ship fast: GPU snapshotting for cold start, serverless GPU infra, autoscaling, and a team that moves at our speed.
Modal@modal

Frontier models for video and embodied reasoning will push the envelope for Physical AI. Try out @perceptroninc's Mk1, hosted on Modal.

English
0
3
20
4.4K
Modal
Modal@modal·
New replicas of @vllm_project and @sgl_project servers start up 3-10x faster on Modal. Read the article to learn how -- from GPU health management to CUDA context checkpointing.
Modal tweet media
Charles 🎉 Frye@charles_irl

Inference isn't everything, but it does require a new stack -- not Kubernetes, not SLURM. At @modal, we dove deep to build that stack. In this blog post we explain how, from compute management & cloud-native cacheing to CRIU & GPU checkpointing. modal.com/blog/truly-ser…

English
3
16
184
26.9K
Modal
Modal@modal·
On May 30th, we're partnering with @OpenAIDevs and @AntlerGlobal to host an Autoresearch Systems Hackathon to tackle problems in data and compute-intensive domains.
English
4
15
132
13.2K
Modal retweetledi
Charles 🎉 Frye
Charles 🎉 Frye@charles_irl·
New blog post about a perf feature @saatwiknagpal added to @sgl_project: the CUDA IPC Pool Handle Cache. Lots of people ask me if they need to know GPU arcana to get into inference engineering. The answer is no, and this post is a great example of why! modal.com/blog/boosting-…
English
3
21
200
22.5K
Erik Dunteman
Erik Dunteman@erikdunteman·
Goddamn I just love building with @modal. It's just so good as a product. I've thought this for years and it remains the case.
English
9
1
61
5.9K
Modal
Modal@modal·
ES matched or outperformed GRPO in several runs, especially when training data was limited. Running on Modal, the whole experiment used less than half the platform code of comparable setups and wrapped up in under 2 days.
Modal tweet media
English
1
0
6
2K
Modal
Modal@modal·
We wanted to know if Evolution Strategies could beat GRPO for RL. We teamed up with @AEStudioLA to find out, using Lean theorem proving as our experiment's foundation.
Modal tweet media
English
3
7
70
10.5K
Modal
Modal@modal·
@PrathmeshBhat19 Hi Pratt! Glad you're loving Modal. You can email support @ modal .com and someone will take a look 💚
English
2
0
1
87
Pratt
Pratt@PrathmeshBhat19·
@modal who to contact regarding support? Love the app but accidentally kept 2xh100 running for 12+ hours ( got a huge bill)
English
1
0
0
37