[test] speedup TRT accuracy tests #5388
Closed
Conversation
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
Signed-off-by: Omer Ullman Argov <[email protected]>
Signed-off-by: Omer Ullman Argov <[email protected]>
Signed-off-by: Omer Ullman Argov <[email protected]>
This reverts commit 3ec8d8f.
|
/bot run |
|
PR_Github #9562 [ run ] triggered by Bot |
|
PR_Github #9562 [ run ] completed with state |
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Outdated suggestions cannot be applied.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.
Speedup TRT accuracy tests
TRT accuracy tests involve
convertandbuildstages, and different cases of the same suite often use the exact same flags toconvert_checkpoint.pyor totrtllm-build.This PR introduces a new
TempDirLRUCachethat caches the checkpoint and engine directories from each test case, and reuses them in case a case uses the exact same flags.This optimization can potentially reduce the test time of some cases by several minutes.