fix: Remove hardcoded lmi config name in ModelBuilder optimize#5749
Open
nargokul wants to merge 2 commits intoaws:master-v2from
Open
fix: Remove hardcoded lmi config name in ModelBuilder optimize#5749nargokul wants to merge 2 commits intoaws:master-v2from
nargokul wants to merge 2 commits intoaws:master-v2from
Conversation
Replace hardcoded config_name='lmi' in ModelBuilder.optimize() with the model's dynamically resolved default config name. The JumpStart metadata for models like llama-3-1-8b-instruct no longer includes an 'lmi' config, causing ValueError during optimization. Also fix test_jumpstart_session_with_config_name to use the model's resolved config_name instead of hardcoding 'tgi', and update unit test assertions in test_js_builder.py accordingly.
The JumpStart metadata update changed the default config from 'lmi' to 'max_context_best_price_performance', which adds extra environment variables to container_defs. Updated all three test assertions to use ANY for the Environment dict and separately verify only the specific env vars each test cares about (OPTION_QUANTIZE, OPTION_TENSOR_PARALLEL_DEGREE, OPTION_SPECULATIVE_DRAFT_MODEL).
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Replace hardcoded config_name='lmi' in ModelBuilder.optimize() with the model's dynamically resolved default config name. The JumpStart metadata for models like llama-3-1-8b-instruct no longer includes an 'lmi' config, causing ValueError during optimization.
Also fix test_jumpstart_session_with_config_name to use the model's resolved config_name instead of hardcoding 'tgi', and update unit test assertions in test_js_builder.py accordingly.
Issue #, if available:
Description of changes:
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.