-
Notifications
You must be signed in to change notification settings - Fork 608
Arm backend: Add argument to list used fallback ops for run.sh #5815
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Arm backend: Add argument to list used fallback ops for run.sh #5815
Conversation
This make it possible to specify what non EthosU ops to include in the build from the command line when running run.sh. As run.sh supports running models specified in files the hardcoded approch is inconvinent. Signed-off-by: Zingo Andersen <[email protected]> Change-Id: I98deb8a73d5178641a328d1200f04ec800c1b433
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/5815
Note: Links to docs will display an error until the docs builds have been completed. ❌ 1 New Failure, 1 Unrelated FailureAs of commit e7b3c23 with merge base 393553c ( NEW FAILURE - The following job has failed:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
ok for now but let's add a comment saying watch out for size bloats if you are not using selective builds.
|
||
help() { | ||
echo "Usage: $(basename $0) [options]" | ||
echo "Options:" | ||
echo " --model_name=<MODEL> Model to run, can be a builtin, examples/models or a filename Default to all builtin models" | ||
echo " --aot_arm_compiler_flags=<FLAGS> Only used if --model_name is used Default: ${aot_arm_compiler_flags}" | ||
echo " --portable_kernels=<OPS> Comma separated list of portable (non delagated) kernels to include Default: ${portable_kernels}" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this can blow up in size as the other issue was saying, we can take in a yaml which should also allow you to specify dtype etc.
@digantdesai has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
|
||
help() { | ||
echo "Usage: $(basename $0) [options]" | ||
echo "Options:" | ||
echo " --model_name=<MODEL> Model to run, can be a builtin, examples/models or a filename Default to all builtin models" | ||
echo " --aot_arm_compiler_flags=<FLAGS> Only used if --model_name is used Default: ${aot_arm_compiler_flags}" | ||
echo " --portable_kernels=<OPS> Comma separated list of portable (non delagated) kernels to include Default: ${portable_kernels}" |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
so softmax is the default but it gets overwritten right? Can we make it clear in the help msg?
@digantdesai merged this pull request in 00d804c. |
This make it possible to specify what non EthosU ops to include in the build from the command line when running run.sh. As run.sh supports running models specified in files the hard coded approach is incontinent.