@modal and @tensarahq i like math and ml

hbm
Joined September 2019
Include

Only show posts containing:

Exclude

Hide posts containing:

Time range
-
Minimum likes
you should run some inference on it :)
98
Replying to @charles_irl
this is how i imagine kv transfer
5
172
Replying to @marksaroufim
its a megakernel because it is 12k LoC
4
429
Harmya retweeted
The secret to Modal's speed is our custom lazily loaded container filesystem, ImageFS. ImageFS is built on a massive tiered distributed filesystem, layering local NVMe disks, regional and p2p caches, and global blob stores. When we launched VM Sandboxes this month, we wanted to make sure they could take advantage of ImageFS in the same way our gVisor containers do. To do that, we built out a new filesystem stack that tricks a VM's ext4 driver into thinking it's talking to a normal disk.
14
30
5
543
52,532
relax pal
1
11
370
one of the best things you can do is join modal and become a GDE (Gongy Deployed Engineer)
My Modal journey started in SF 4.5 years ago as an intern. Since then I've learnt so much from my mentor @akshat_b and our two desks in a shared WeWork have become hundreds in a new SF office. What compels me about Modal's growth is not the number but the mindset. You can hire to grow 2x per year, but any more and you damage culture. How do you scale growth past 2x? Grow the people. This is most important thing Modal has done -- it's figure out how to find people with high potential, and grow them 4-5x per year. It creates a happy culture, and the company grows way faster than you can hire. Come to mentor, and come to grow. modal.jobs
24
653
Today we're announcing that Modal has crossed $1B in annualized run rate, as well as raised a $750M Series D at a $15.75B valuation, led by @Accel. Since our Series C, usage has tripled and we’ve grown more than 15x year-over-year. We are deeply grateful to the developers and companies building on Modal. There's still so much more to build, and we can't think of a better time to be building software.
1
17
676
charles’ title is “head chef” btw, straight cooking
We updated our LLM Engine Advisor with the latest results from @modal Dedicated Endpoints. With just a few clicks and a single CLI command, you can select and deploy a reasonable open-weights inference service. modal.com/llm-almanac/adviso…
1
16
627
this modal guy is cooking rn
1
2
53
1,919
Replying to @AryaTschand @modal
welcome :) so excited
1
1
199
powering the jevolution
. @modal moves mountains to make models manifest! Our man in pink @CompleteSkeptic will be speaking at Runtime, you won't want to miss it.
2
6
1,376
Replying to @EuclidStellar
depends on the config! but usually TTFT suffers
22
how sglang scheduler looks at the decode step when a long prefill comes in
1
2
27
1,995
deepseek doing a minor version bump of v4 flash
1
5
609
many inference companies focus on tpm tps ttft -- i would much rather focus on more important things like understanding how a rat can be such a good chef
3
2
28
1,847