Fix config.per_layer_config[layer_type] lookup speed - #47539
Merged
Merged
Conversation
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Contributor
There was a problem hiding this comment.
Pull request overview
This PR optimizes heterogeneous configuration access by making config.per_layer_config[layer_type] significantly faster, addressing slow initialization when using heterogeneous layer_types (e.g., Gemma 4 in vLLM).
Changes:
- Reworked
_PerLayerConfigView.__getitem__forstrkeys to avoid constructing per-layer configs just to check homogeneity. - Added unit tests covering layer-type indexing behavior (homogeneous, heterogeneous, missing/unknown layer types).
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
src/transformers/integrations/heterogeneity/configuration_utils.py |
Refactors layer-type lookup to compare per-layer overrides directly and return the resolved config. |
tests/heterogeneity/test_configuration_utils.py |
Adds coverage for indexing per_layer_config by layer_type, including error cases. |
|
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. |
Contributor
CI recapDashboard: View test results in Grafana |
stevhliu
pushed a commit
to stevhliu/transformers
that referenced
this pull request
Jul 30, 2026
…7539) Fix `config.per_layer_config[layer_type` lookup speeds Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Sainava
pushed a commit
to Sainava/Sai-transformers
that referenced
this pull request
Aug 3, 2026
…7539) Fix `config.per_layer_config[layer_type` lookup speeds Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
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
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.
This was causing very slow init when trying to use Gemma 4 in vLLM with the new heterogeneous configs.