Lazy load heavy deps for AI image descriptions#19055
Merged
Merged
Conversation
Contributor
|
How about when AI image description is switched from enabled to disabled? does the memory occupied by numpy free up? Or must NVDA be restarted? |
Contributor
Author
Once imported, packages remain in memory until the process restarts.
Yes, I think. |
SaschaCowley
pushed a commit
that referenced
this pull request
Jan 11, 2026
Reverts: - #18475 - #19036 - #19024 - #19055 - #19057 - #19178 - #19243 - #19327 - Partial revert: #19342 ### Issues fixed Fixes #19298 ### Issues reopened Reopens #16281 ### Reason for revert / Can this PR be reimplemented? If so, what is required for the next attempt The current implementation of AI image descriptions yields low quality captions from a 3 year old model (see #19298). The current implementation also requires using numpy, which hogs RAM, slows initialization, and increases the weight of the installer. An attempt was made to convert this to C++ using WinML and Windows ONNX runtimes as per #18662. This would have removed numpy, and improved flexibility for using different models in the future. Unfortunately, this was not found to be feasible, as ONNX C++ fails to work via 64bit emulation on ARM (microsoft/onnxruntime#15403). This means we have the following options for image descriptions: 1. Continue to use the python onnxruntime, and accept the RAM and storage hits. Instead, improve the quality of the captioner with better models such as [git-base-coco](https://huggingface.co/microsoft/git-base-coco) or [blip2](https://huggingface.co/Salesforce/blip2-opt-2.7b-coco). 2. Wait until MS builds ARM64EC into C++ ONNX (blocked by microsoft/onnxruntime#15403) 3. Attempt to build our own fork of ONNX with ARM64EC 4. Build a separate ARM native installer of NVDA, offer as an alternative to allow for ARM devices to do image descriptions with numpy. 5. Release the feature on C++ without support for ARM devices. All of these options require a significant amount of work. As such, sadly this feature is not ready for a stable release. Instead this code will be moved to a feature branch, until ONNX C++ matures such as fixing microsoft/onnxruntime#15403. Additionally, ONNX C++ runtimes are only available through the experimental 2.0 version of the Windows App SDK, and requires you to build your own headers from it. I think this feature will be blocked until microsoft/onnxruntime#15403 is implemented and the 2.0 version of the Windows App SDK becomes stable. Future re-implementations should also consider using higher quality, more modern models.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Link to issue number:
Fixes #19031
Summary of the issue:
import numpy directly may cause high memory useage when AI image descriptions is disabled.
Description of user facing changes:
The memory usage caused by NumPy will only occur when the AI image descriptions is loaded.
Description of developer facing changes:
Move captioner.py into a captioner/ package to support lazy import of large libraries such as numpy and onnxruntime. This reduces startup time and memory usage to some extent.
Description of development approach:
None
Testing strategy:
Observe memory useage and start time of NVDA
Known issues with pull request:
None
Code Review Checklist: