@modal and @tensarahq i like math and ml

hbm
Joined September 2019
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
52,594
relax pal
1
11
375
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
656
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
680
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
630
this modal guy is cooking rn
1
2
53
1,921
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
1,378
how sglang scheduler looks at the decode step when a long prefill comes in
1
2
27
1,997
deepseek doing a minor version bump of v4 flash
1
5
610
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
1,848
multi modal model on modal
1
1
24
1,823
which of your favorite token brokers are contributing back to open source ai? shall we count the ways? a slice of data: number of PRs upstreamed and merged into the most popular oss inference engines, by PR contributor org
17
17
16
225
56,383
The only part of this article I used AI for was the cover photo, I swear. Link to session - chatgpt.com/share/6aa3732d-0… View article
4
3
1
36
2,747
goated, we are going to have ornithopters now
I left a16z to start Ixian Robotics! I’m very grateful for the people I got to learn from at a16z, and excited to be building again. The last couple of months have felt like knocking down dominoes I’ve spent years putting up. Wrote a bit about the last year and what I want to build next: zietek.dev/blogs/starting_ix…
5
718
best is implied btw
infra for inference...union sq sf
1
20
1,970
how our team was moving to provide y'all with two models in two days
GLM 5.3, the latest flagship model by @Zai_org, is now available on Modal.
2
1
75
4,486
holy cache hit rate
found out we're serving 40% of Kimi K3 traffic on OpenRouter ... the guy working on it is tired. anyone wanna help us work on inference?
23
3,818
can confirm he is goated
one of the top 5 best researchers I've worked with is exploring dropping his PhD for industry. bg in optimization & interpretability, just wrapped an internship at Apple MLR w glowing recs if you're hiring for research roles (esp w scope to publish) dm & happy to intro
26
6,230
summary: what if kernel big
The megakernel literature, summarized
8
1,339
chonk model on a chonk infra provider, meant to be
Qwen3.8-2.4T-A95B by @Alibaba_Qwen and @alibaba_cloud is now available on Modal. Served with a custom DFlash speculator trained on tool-call-heavy data. Full 1M context window.
2
1
20
2,366