Introduce inference: block to pytorch_config.yaml#3104
Closed
maximpavliv wants to merge 4 commits intomainfrom
Closed
Introduce inference: block to pytorch_config.yaml#3104maximpavliv wants to merge 4 commits intomainfrom
inference: block to pytorch_config.yaml#3104maximpavliv wants to merge 4 commits intomainfrom
Conversation
Contributor
|
Works great on new projects. |
Member
|
Any issues with compat on older TF projects, no right? |
MMathisLab
approved these changes
Oct 1, 2025
Contributor
Author
|
@MMathisLab no, this doesn't introduce any chances on the TF-backend part. This PR no longer has any diffs against main because its commits were included in #3105. Closing as redundant. |
Contributor
Tested these series of PRs regarding inference on older TF projects and analyzed some videos. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Main changes:
Introduced
MultithreadingConfigandInferenceConfigdataclasses, includingfrom_dictandto_dicthelper methods for convenient YAML and dict conversion.Updated
InferenceRunner(and its child classes) to accept anInferenceConfigobject instead of separate multithreading arguments.Added an
inference:block with default multithreading values topytorch_config.yamlwhen it is created.inferenceblock is missing in an existing config, default values are used to maintain backwards compatibility.Notes:
Currently, only the multithreading parameters are included in this PR.
Configuration for
torch.compileandtorch.autocastwill be added in future PRs.