Adding documentation emphasizing GPU requirements (NIVIDA + Apple Silicon) #2071
Conversation
WalkthroughThis pull request focuses on updating documentation across multiple files to improve clarity and accessibility of information about training hardware support and installation instructions for SLEAP. The changes include adding a new entry to the table of contents, creating a dedicated section on training hardware requirements, and providing more explicit guidance about GPU support for NVIDIA GPUs and Apple Silicon Macs. Changes
Possibly related PRs
Poem
📜 Recent review detailsConfiguration used: CodeRabbit UI 📒 Files selected for processing (1)
🚧 Files skipped from review as they are similar to previous changes (1)
Thank you for using CodeRabbit. We offer it for free to the OSS community and would appreciate your support in helping us grow. If you find it useful, would you consider giving us a shout-out on your favorite social media? 🪧 TipsChatThere are 3 ways to chat with CodeRabbit:
Note: Be mindful of the bot's finite context window. It's strongly recommended to break down tasks such as reading entire modules into smaller chunks. For a focused discussion, use review comments to chat about specific files and their changes, instead of using the PR comments. CodeRabbit Commands (Invoked using PR comments)
Other keywords and placeholders
CodeRabbit Configuration File (
|
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
docs/guides/training.rst (1)
62-75: LGTM! Clear and comprehensive hardware support documentation.The new section effectively communicates hardware requirements and limitations. Consider adding links to the installation guide for more detailed GPU setup instructions.
Add a reference to the installation guide:
For best results, we recommend using an NVIDIA GPU or Apple Silicon Mac for training. + +For detailed GPU setup instructions, see the [Installation Guide](../installation.md#gpu-support).
📜 Review details
Configuration used: CodeRabbit UI
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (3)
docs/guides/index.md(1 hunks)docs/guides/training.rst(2 hunks)docs/installation.md(2 hunks)
🔇 Additional comments (2)
docs/guides/index.md (1)
46-46: LGTM! The training guide entry is properly added to the table of contents.
The addition improves documentation accessibility by making the training guide directly navigable.
docs/installation.md (1)
19-21: LGTM! Well-placed and clear GPU support information.
The note effectively communicates hardware requirements early in the installation process, helping users understand compatibility before proceeding with installation.
This is a good suggestion, I made the changes and added the link to installation.md#gpu-support from the training guide rst. |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
docs/tutorials/initial-training.rst (1)
9-9: LGTM! Clear and well-positioned hardware requirements notice.The note effectively communicates the supported hardware platforms and provides helpful alternatives for users without supported GPUs. The placement at the beginning of the tutorial is strategic and helps prevent users from running into issues later.
Consider enhancing the note with:
- Minimum GPU requirements (e.g., CUDA compute capability, minimum memory)
- Expected training performance differences between supported platforms
- Direct link to GPU setup instructions in the installation guide
This tutorial assumes you have an NVIDIA GPU or an Apple Silicon Mac, and that TensorFlow is able to use your GPU. Training on other GPU architectures may fail. If you don't have a supported GPU or you're having trouble getting it to work, you can run training and inference in the cloud. See our :ref:`colab` guide! Or take a look at our other :ref:`guides` about running SLEAP on remote machines. + + **Minimum Requirements:** + - NVIDIA GPU: CUDA compute capability 3.5 or higher, 8GB+ memory recommended + - Apple Silicon: M1/M2/M3 chip with 8GB+ memory + + For detailed GPU setup instructions, see :ref:`gpu-setup`.
Done! Here is the screenshot: 
|
Description
As requested in Issue #2016 I have added some up front documentation that makes it clearer that only NVIDIA GPUs and Apple Silicon Macs are supported. I added it to the installation documentation right at the top of the page under the installation widget as a note. Let me know if this is too bold, but should help to avoid those types of issues in the future.
Here is a screenshot of the installation docs:
I also added a Training Hardware Support section in the bottom of the Training Guide. Also I noticed that the training guide was not in the Guide menu, so I added Training With GUI to the guide menu as well.
Here is a screenshot of the Training guide and menu addition:
Types of changes
Does this address any currently open issues?
[list open issues here]
Outside contributors checklist
Thank you for contributing to SLEAP!
❤️
Summary by CodeRabbit
New Features
Documentation