Create unified script and workflow for llama-fast models validationin #94
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
facebook-github-bot
added
the
CLA Signed
guangy10
force-pushed
the
et_validation
branch
6 times, most recently
from
4e3c734 to
8a57c22
Compare
guangy10
force-pushed
the
et_validation
branch
8 times, most recently
from
eb57f3f to
d949b12
Compare
|
It's not fully ready for review as the newly added models will require running the hg_converter first, but the CI part should be okay. My main goal is to run model valdiation jobs on macOS x86 (supported), macOS M1/ARM (supportted), Linux x86 (supported), Linux ARM (?). @huydhn @kit1980 I know pytorch test-infra has lots of runners, but not sure if those are self-hosted and whether we can use one here. Also is it possible if we'd like to run the Android/iOS emulator on an host platform for the correctness validation? |
guangy10
force-pushed
the
et_validation
branch
5 times, most recently
from
9c19e53 to
8b0b17a
Compare
|
The inference error using ExecuTorch is fixed in #122 |
|
The macos x86 issue is same as what Scott reported early when build ExecuTorch. Let's disable it in this PR and move on. Will have to re-enable it once the issue is cleared. |
guangy10
changed the title
mikekgfb
approved these changes
Apr 11, 2024
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
malfet
pushed a commit
that referenced
this pull request
Jul 17, 2024
malfet
pushed a commit
that referenced
this pull request
Jul 17, 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.
To run the workflow across different platforms for supported models, simply run the top-level script
bash ./scripts/workflow.sh [cpu | cuda], which relies on bunch of scripts under.ci/scripts. So CI and local dev are running pretty much same scripts. For the platforms that are not supported in GitHub CI, we can manually run the script on the target platforms