Master benchmark feature merge master #4661
Merged
Conversation
This file contains 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
* fix: parsing * fix: commit tests * fix: types * updated * fix
Co-authored-by: Nikhil Kulkarni <nikhilsk@amazon.com>
* feature: support session tag chaining for training job * fix: resolve typo * fix: resolve typo and build failure * fix: resolve typo and unit test failure --------- Co-authored-by: Jessica Zhu <jessicazhu3@106775307+jessicazhu3@users.noreply.github.com>
* breaking: set default allow_pickle param to False * breaking: fix unit tests and linting NumpyDeserializer will not allow deserialization unless allow_pickle flag is set to True explicitly * fix: black-check --------- Co-authored-by: Ashwin Krishna <ashwikri@amazon.com>
* fix: invalid component name * tests * format * fix vulnerable model integ tests llama 2 * updated * fix: training dataset location
* Update skipped flaky tests * flake8 * format * format
* chore: release tgi 2.0.1 * minor fix --------- Co-authored-by: Zhaoqi <52220743+zhaoqizqwang@users.noreply.github.com>
* Add ReadOnly APIs * Resolving PR review comments * Resolve PR review comments * Refactoring * Refactoring * Add Caching * Refactore * Resolving conflicts * Add Unit Tests * Fix Unit Tests * Fix unit tests * Fix UT * Refactoring * Fix Integ tests * refactoring after Notebook testing * Fix code styles --------- Co-authored-by: Jonathan Makunga <makung@amazon.com>
* tag config name * format * resolving comments * format * format * update * fix * format * updates inference component config name * fix: tests
…ws#4614) * Add funtionalities to get and set deployment config * Resolve PR comments * ModelBuilder-JS * Add Unit tests * Refactoring * Testing with Notebook * Test backward compatibility * Remove Accelerated column if all not enabled * Fix docstring * Resolved PR Review comments * Docstring * increase code coverage --------- Co-authored-by: Jonathan Makunga <makung@amazon.com>
* Add funtionalities to get and set deployment config * Resolve PR comments * ModelBuilder-JS * Add Unit tests * Refactoring * Testing with Notebook * Test backward compatibility * Remove Accelerated column if all not enabled * Fix docstring * Resolved PR Review comments * Docstring * increase code coverage * Testing fix with Notebook * Only fetch instance rate metrics if not present * Increase code coverage --------- Co-authored-by: Jonathan Makunga <makung@amazon.com>
Co-authored-by: Jonathan Makunga <makung@amazon.com>
…aws#4625) * require config_name and instance_type in set config * docstring * add supported instance types check * add more tests * format * fix tests
* Init Deployment configs outside Model init. * Testing with NB * Testing with NB-V2 * Refactoring, NB testing * NB Testing and Refactoring * Testing * Refactoring * Testing with NB * Debug * Debug display API * Debug with NB * Testing with NB * Refactoring * Refactoring * Refactoring and NB testing * Testing with NB * Refactoring * Prefix instance type with ml * Fix unit tests --------- Co-authored-by: Jonathan Makunga <makung@amazon.com>
* Use separate tags for inference and training * format * format * format * format
* Filter down Benchmark Metrics * Filter down Benchmark Metrics * Testing NB * Testing MB * Testing * Refactoring * Unit tests * Display instance type first, and instance rate last * Display unbalanced metrics * Testing with NB * Testing with NB * Debug * Debug * Testing with NB * Testing with NB * Testing with NB * Refactoring * Refactoring * Refactoring * Unit tests * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Custom lru * Refactoring * Debug * Config ranking * Debug * Debug * Debug * Debug * Debug * Ranking * Ranking-Debug * Ranking-Debug * Ranking-Debug * Ranking-Debug * Ranking-Debug * Ranking-Debug * Debug * Debug * Debug * Debug * Refactoring * Contact JumpStart team to fix flaky test. test_list_jumpstart_models_script_filter --------- Co-authored-by: Jonathan Makunga <makung@amazon.com>
Captainia
approved these changes
May 7, 2024
evakravi
approved these changes
May 7, 2024
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.
Issue #, if available:
Description of changes:
Merge master.
Testing done:
Merge Checklist
Put an
xin the boxes that apply. You can also fill these out after creating the PR. If you're unsure about any of them, don't hesitate to ask. We're here to help! This is simply a reminder of what we are going to look for before merging your pull request.General
Tests
unique_name_from_baseto create resource names in integ tests (if appropriate)By submitting this pull request, I confirm that my contribution is made under the terms of the Apache 2.0 license.