Allow tests to run in t.compile #724
Open
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
Kacper-Pietkun
requested review from
kzawora-intel,
madamczykhabana,
michalkuligowski,
mgawarkiewicz,
vivekgoe and
afierka-intel
as code owners
Kacper-Pietkun
force-pushed
the
dev/kpietkun/tests_compile
branch
10 times, most recently
from
bbf9258 to
02a4a21
Compare
Kacper-Pietkun
force-pushed
the
dev/kpietkun/tests_compile
branch
from
02a4a21 to
10bf5ee
Compare
Kacper-Pietkun
force-pushed
the
dev/kpietkun/tests_compile
branch
from
10bf5ee to
48d02da
Compare
anko-intel
reviewed
Jan 29, 2025
| @@ -139,7 +139,7 @@ def start_engine(): | |||
|
|
|||
| return AsyncLLMEngine.from_engine_args( | |||
| AsyncEngineArgs(model="facebook/opt-125m", | |||
| enforce_eager=True, | |||
| enforce_eager=False, | |||
There was a problem hiding this comment.
Do we eliminate this way some eager tests ? or is it used only in prepared for torch compile?
|
|
||
| # skip cuda graph creation for fast test. | ||
| "enforce_eager": True, | ||
| # skip cuda graph creation for fast test. |
There was a problem hiding this comment.
Maybe
Suggested change
| # skip cuda graph creation for fast test. | |
| # skip graph creation for fast test. |
|
Before merging a change, it is required to check which tests truly need model compilation (use torch.compile underneath). It is unnecessary to modify tests that do not do that. |
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Outdated suggestions cannot be applied.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.
Currently when setting
PT_HPU_LAZY_MODE=0most tests would run only in eager mode. This fix changes this behavior.