finds.dev← search

// the find

ahkarami/Deep-Learning-in-Production

★ 4,379 · updated Nov 2024

In this repository, I will share some useful notes and references about deploying deep learning-based models in production.

A link dump of tutorials, tools, and articles about deploying deep learning models in production, organized by framework (PyTorch, TensorFlow, Keras, MXNet). No code, no tooling, no original content — just a heavily annotated list of external URLs. Aimed at ML practitioners who want a starting point for deployment reading.

Covers a genuinely wide surface area: model serving, quantization, mobile/edge deployment, MLOps, GPU management, and distributed training all in one place. The framework-by-framework organization makes it easy to find PyTorch-specific or TensorFlow-specific material without wading through everything. Some of the links point to legitimately good resources (TorchServe, Triton, ONNX, TensorRT) that save real research time. The MLOps section specifically links to several free full courses, which is more useful than most curated lists.

This is a bookmark file, not a repository — there is no runnable code, no examples to clone and try, and no original explanation of anything. A large fraction of the links are from 2018–2019 and reference frameworks and APIs that have changed significantly; Caffe2 is essentially dead, MXNet is in maintenance mode, and several linked blog posts describe patterns that PyTorch and TensorFlow have since replaced with native tooling. The UI/frontend section (AngularJS vs React in 2018, Adobe Typekit) has no connection to deep learning deployment and looks like it was added to pad the repo. Last meaningful update was 2024 but most content predates 2022.

View on GitHub →

// want more like this?

We dig through GitHub every week and send a few repos picked for what you actually care about — each with an honest take like this one.

Get finds in your inbox → Search again →