Modal
@modal

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

 New York City
modal.com
Joined July 2022
310 Photos and videos
Article

Scaling to 1 million concurrent sandboxes in seconds

This post was written by Colin Weld and Connor Adams. Read it here or on our blog. At Modal, we build sandboxes, among other things. Agents run in sandboxes, and agents are eating software. Today,

26
97
922
515,056
Article

Product Updates: VM Sandboxes, Lower-latency routing, Domain allowlisting for Sandboxes, and More

馃實 Lower latency with regional routing To improve latency, Functions can now run closer to where they're called from. Instead of routing through the default US East region, you can send a Function's

4
1
75
6,913
Article

Modal's Series C: Raising $355M at a $4.65B valuation

We鈥檝e raised $355 million after growing fivefold since September, surpassing $300 million in annualized revenue. Our valuation is $4.65B post-money in a round led by @generalcatalyst and @Redpoint,

33
44
537
630,394
Article

Boosting multimodal inference performance by >10% with a single Python dictionary

tl;dr: Multimodal models are promising, but inference engines haven't been optimized for them yet. We profiled SGLang鈥檚 scheduler on a multimodal workload and identified an opportunity to replace

3
10
123
14,355
Article

Autoscaling Autoresearch: Give your agents elastic GPUs

Following @karpathy-san鈥檚 banger release of autoresearch, many are embracing the use of AI to accelerate AI research. But autoresearch introduces a new version of a familiar problem: how do you give

3
32
362
86,807
Article

Product Updates: RTX Pro 6000, Command K, Sandbox FS API and more

鈿TX Pro 6000 is now available on Modal NVIDIA's RTX Pro 6000 Blackwell is now available on Modal with a single line of code. The Blackwell generation's answer to the workhorse A10 and L40S GPUs,

1
2
38
3,509
Load more