BentoML VS TextSecure

Link to GitHub -->

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

Elastic License 2: https://github.com/bentoml/bentoctl/blob/v0.3.1/LICENSE.md which also applies to their Yatai kubernetes thing, but strangely not (yet?) to the similarly named repo which is Apache-2: https://github.com/bentoml/BentoML/blob/main/LICENSE

Using a general-purpose framework such as FastAPI involves writing a lot of boilerplate code just to get your API endpoint up and running. If deploying a model for a demo is the only thing you are interested in and you do not mind losing some flexibility, you might want to use a specialized serving framework instead. One example is BentoML, which will allow you to get an optimized serving endpoint for your model up and running much faster and with less overhead than a generic web framework. Framework-specific serving solutions such as Tensorflow Serving and TorchServe typically offer optimized performance but can only be used to serve models trained using Tensorflow or PyTorch, respectively.

BentoML - BentoML is a flexible, high-performance framework for serving, managing, and deploying machine learning models.

Also mlflow is not that optimized because it doesnt microbatch like torchserve/tfserving/bentoml. https://github.com/bentoml/BentoML/tree/master/benchmark

Moxie's reasons for disallowing Signal distribution via F-droid always rang a little flat to me ( https://github.com/signalapp/Signal-Android/issues/127 ). Lots of chatter about the supposedly superior security model of Google Play Store, and as a result fewer eyes independently building and testing the Signal code base. Everyone is entitled to their opinions, but independent and reproducible builds seem like a net positive for everyone. Always struggled to understand releasing code as open source without taking advantage of the community's willingness to build and test. Looking at it in a new light after the XZ backdoor, and Jia Tan's interactions with other FOSS folk.

https://github.com/signalapp/Signal-Android/issues/7409

> We've discussed at length why this is not possible, but if you have more thoughts then please visit the forums. Please try not to open duplicate issues in the future, even if you feel like something is important.

I wonder why this is "not possible"

Signal has documentation on how to reproduce their Play Store builds and compare them with what you've installed locally:

https://github.com/signalapp/Signal-Android/blob/main/reprod...

There's nothing on Signal blog as of yet, but Signal's git repository was tagged with v7.0.0 yesterday and we can see from the commit history since the previously tagged version (v6.74.4) that there will be a setting to hide one's phone number [1], as well as disabling the previous default behavior of advertising that one is on Signal to all their contacts already using it [2].

[1] https://github.com/signalapp/Signal-Android/commit/8797236b5... (PNP stands for "Phone Number Privacy")

[2] https://github.com/signalapp/Signal-Android/commit/6097e6c30...

Signal works the same but without the user tracking from Meta/Facebook. Many people use it as well but I'm surprised that a majority sticks to WhatsApp.

Telegram and Signal solve this.