This repository was archived by the owner on May 23, 2024. It is now read-only.
fix: Use default model name when model name is None #214
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Outdated suggestions cannot be applied.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.
Issue #, if available:
Description of changes:
The
model_name
parameter when making a non-MME inference request, in the presence of a user's inference script, is treated asNone
by the python service for SM inference. This means that thecontext
passed to the inference handler does not have a validmodel_name
attribute.Therefore, GRPC-based inference requests for a model cannot be programmatically configured, and must instead always be hardcoded in the user's inference script. This requirement makes it harder to compile a model, or to use it with SageMaker Inference Recommender to produce a Neo-compilation-compatible model.
This PR makes a change to
tfs_utils.py
to use thedefault_model_name
, obtained from theTFS_DEFAULT_MODEL_NAME
environment variable, as the final option in case the input model_name isNone
and the request attributes do not contain the model name.By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.