Add ability to pass model_dir to .ci/scripts/test_huggingface_optimum #13116
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13116
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 2 New Failures, 1 Cancelled Job, 1 Unrelated FailureAs of commit 4815b11 with merge base 7750116 ( NEW FAILURES - The following jobs have failed:
CANCELLED JOB - The following job was cancelled. Please retry:
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. |
meta-cla
bot
added
the
CLA Signed
This PR needs a
|
| parser.add_argument("--model", type=str, required=True) | ||
| parser.add_argument("--recipe", type=str, required=True) | ||
| parser.add_argument("--quantize", action="store_true", help="Enable quantization") | ||
| parser.add_argument("--model_dir", type=str, required=False) |
| model_dir=args.model_dir, | ||
| recipe=args.recipe, | ||
| quantize=args.quantize, | ||
| run_only=False, |
There was a problem hiding this comment.
why does this depend on the model_dir type
There was a problem hiding this comment.
It doesn't, I'll remove it
| test_fn( | ||
| model_id=model_id, | ||
| model_dir=tmp_dir, | ||
| recipe=args.recipe, | ||
| quantize=args.quantize, |
…pytorch#13116) Adds ability to specify model_dir to optimum test script. This is convinient if you want the pte file for local debugging. If no model_dir is specified, a temp directory is created.
Adds ability to specify model_dir to optimum test script. This is convinient if you want the pte file for local debugging. If no model_dir is specified, a temp directory is created.