Benchmark app and testspec update #5240
Closed
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5240
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New FailureAs of commit e7003c5 with merge base c5c121b ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
kirklandsign
force-pushed
the
benchmark-app-update
branch
2 times, most recently
from
b9c5365
to
3d2a3d7
Compare
guangy10
approved these changes
Sep 11, 2024
kirklandsign
force-pushed
the
benchmark-app-update
branch
from
3d2a3d7
to
64f1476
Compare
kirklandsign
force-pushed
the
benchmark-app-update
branch
from
64f1476
to
8d4e201
Compare
guangy10
approved these changes
Sep 12, 2024
|
@kirklandsign has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
shoumikhin
approved these changes
Sep 12, 2024
|
@kirklandsign merged this pull request in 8874de2. |
huydhn
reviewed
Sep 13, 2024
| - adb -s $DEVICEFARM_DEVICE_UDID shell "chmod 664 /data/local/tmp/minibench/*.bin" | ||
| - adb -s $DEVICEFARM_DEVICE_UDID shell "chmod 664 /data/local/tmp/minibench/*.pte" | ||
| - adb -s $DEVICEFARM_DEVICE_UDID shell "ls -la /data/local/tmp/minibench/" | ||
| - adb -s $DEVICEFARM_DEVICE_UDID shell "run-as org.pytorch.minibench rm -rf files" |
There was a problem hiding this comment.
Ouch, this doesn't work and ends up with run-as: unknown package: org.pytorch.minibench in trunk. That error makes sense because this is pre_test, so I suspect that the app hasn't been installed yet
There was a problem hiding this comment.
Never mind, I realize that the warnings comes from LlamaDemo and ExecuTorchDemo
facebook-github-bot
pushed a commit
that referenced
this pull request
Sep 13, 2024
Summary: After #5240, as the test spec becomes more catered toward Minibench, it doesn't work with LlamaDemo anymore because of the different model path and is currently failing in trunk https://hud.pytorch.org/hud/pytorch/executorch/main/1?per_page=50&name_filter=test-llama-app. I think this job has outlived its usefulness and can be cleaned up. We already have android-perf workflow in its place. guangy10 has already cleaned it up once before, but we have kept it around till the benchmark workflow grows a bit more. Pull Request resolved: #5340 Reviewed By: kirklandsign Differential Revision: D62624109 Pulled By: huydhn fbshipit-source-id: 26e09f965ce0f61cba13a5cbc75acccc67376920
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.
No description provided.