[docs] Distributed inference #12285
Open
[docs] Distributed inference #12285
Conversation
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
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
sayakpaul
reviewed
Sep 5, 2025
| > [!TIP] | ||
| > You can use `device_map` within a [`DiffusionPipeline`] to distribute its model-level components on multiple devices. Refer to the [Device placement](../tutorials/inference_with_big_models#device-placement) guide to learn more. | ||
|
|
||
| ## Model sharding |
There was a problem hiding this comment.
I removed it because it seems more like a "recipe" for progressively and strategically fitting models on a GPU by loading and removing them. I don't think a user is really learning anything new/useful about device_map here compared to the device placement docs to which there is a link at the bottom.
I would suggest removing it or at least moving it to Resources > Task Recipes.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Reduces bloat by removing the
## Model shardingsection because it isn't really about distributed inference (its more selectively loading and deleting models) and doesn't show processing multiple prompts in parallel.