Add IREE numerics test for Llama 3.1 8B FP16 TP8 #394
+435
−364
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
Introduce a Llama 3.1 8B FP16 TP8 test that appears to not have good numerical accuracy. It is compared to an fp64 unsharded torch variant to ensure that the reference is of high accuracy. Refactor the sharded Llama tests. Increase code reuse and use the TorchGenerator in the toy-sized tests. Use the shard_llm_dataset and export_paged_llm_v1 scripts in the test flow to increase their test coverage.
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Outdated suggestions cannot be applied.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.
Introduce a Llama 3.1 8B FP16 TP8 test that appears to not have good numerical accuracy. It is compared to an fp64 unsharded torch variant to ensure that the reference is of high accuracy.
Refactor the sharded Llama tests. Increase code reuse and use the TorchGenerator in the toy-sized tests. Use the shard_llm_dataset and export_paged_llm_v1 scripts in the test flow to increase their test coverage.