some-assembly-required VS BentoML

See also:

"Some Assembly Required: An approachable introduction to assembly" - https://github.com/hackclub/some-assembly-required

https://news.ycombinator.com/item?id=31909183 (587 points | 4 months ago | 125 comments)

Hack Club | Full-time, Part-time or Contract | ONSITE | Vermont, US | https://hackclub.com

Hello friends,

I come from the game dev world where I led the team on the Crash Bandicoot reboot trilogy and helped ship two of the Destiny 2 expansions. I’m now building out a team here at Hack Club that will make inspiring technical and creative projects with and for thousands of the most technical teenagers you’ll probably ever meet.

In the past 3 months, we’ve shipped an open source game console ( https://github.com/hackclub/sprig ) that you can only get by building a game for it, a guide to assembly language that’s now the 4th most popular GitHub repo written in assembly ( https://github.com/hackclub/some-assembly-required ), and a teaser for a game we're producing about love and graphing (https://hack.af/sr ).

For this role, I’m looking for a technical partner-in-crime with a few notches in your belt.

JOB DESCRIP/APPLY: https://hiring.hackclub.com/26020 or email [email protected]

We do this by creating open-source projects which serve the community like a transparent “bank” for nonprofits, a game console you can only get by building a game for it, a guide to assembly language, a cross-country hackathon on a train. Hack Club supports and grows our community by facilitating wholesome social spaces online and in-person.

A recent YC article mentioned this [site] (https://github.com/hackclub/some-assembly-required/)

Some Assembly Required An approachable introduction to assembly that can be read in 30 minutes if you skip code examples. Although it's probably interesting to take a bit more time to try to read them and understand the details.

Some Assembly Required: An approachable introduction to assembly\ (119 comments)

Link to GitHub -->

there are a few tools you can use as "cheat mode" shortcuts to give you a leg up as you're getting started. here's one: https://github.com/bentoml/BentoML

Then you can look into bentoml https://github.com/bentoml/BentoML which is used to deploy ml stuff with many more benifits.

For 2), I am aware of a few options. Triton inference server is an obvious one as is the ‘transformer-deploy’ version from LDS. My only reservation here is that they require the model compilation or are architecture specific. I am aware of others like Bento, Ray serving and TorchServe. Ideally I would have something that allows any (PyTorch model) to be used without the extra compilation effort (or at least optionally) and has some convenience things like ease of use, easy to deploy, easy to host multiple models and can perform some dynamic batching. Anyway, I am really interested to hear people's experience here as I know there are now quite a few options! Any help is appreciated! Disclaimer - I have no affiliation or are connected in any way with the libraries or companies listed here. These are just the ones I know of. Thanks in advance.

In this category I’m a big fan of https://github.com/bentoml/BentoML

What I like about it is their idiomatic developer experience. It reminds me of other Pythonic frameworks like Flask and Django in a good way.

I have no affiliation with them whatsoever, just an admirer.

Github Page: https://github.com/bentoml/BentoML