-
Notifications
You must be signed in to change notification settings - Fork 741
Swap Llava export arg order #14238
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
Swap Llava export arg order #14238
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14238
Note: Links to docs will display an error until the docs builds have been completed. ❌ 6 New Failures, 1 Cancelled Job, 37 Pending, 1 Unrelated FailureAs of commit 3a800cb with merge base 6d8583d ( 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. |
| def _get_prompt_dynamic_shapes(self): | ||
| dim = torch.export.Dim("token_dim", min=2, max=self.max_seq_len) | ||
| text_model_dynamic_shapes = ({0: 1}, {1: dim}) | ||
| text_model_dynamic_shapes = ({1: dim}, {0: 1}) |
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.
nit: 1 and 0 are the dims of a single tensor. So swapping doesnt do anything
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.
also do you even have to specify that the batch is static 1?
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.
{0:1} is the dynamic shapes for the first arg, {1:dim} is for the second arg, so I swap them here
|
@pytorchbot cherry-pick --onto release/1.0 -c feature |
|
❌ 🤖 pytorchbot command failed: Try |
|
@pytorchbot cherry-pick --onto release/1.0 -c critical |
Swaps Llava export arg order, such that forward takes `embeddings, cache_position`, instead of `cache_position, embeddings`. (cherry picked from commit 23acfea)
Cherry picking #14238The cherry pick PR is at #14344 and it is recommended to link a critical cherry pick PR with an issue. The following tracker issues are updated: Details for Dev Infra teamRaised by workflow job |
Swaps Llava export arg order, such that forward takes `embeddings, cache_position`, instead of `cache_position, embeddings`.
Summary
Swaps Llava export arg order, such that forward takes
embeddings, cache_position, instead ofcache_position, embeddings.Test plan
Existing Llava tests