[ET-VK] Fix force_fp16 texture bias being silently rejected for CONTIGUOUS_ANY ops#18779
Merged
[ET-VK] Fix force_fp16 texture bias being silently rejected for CONTIGUOUS_ANY ops#18779
Conversation
…GUOUS_ANY ops Pull Request resolved: #18770 The `force_fp16` path in `TagMemoryMetaPass` applies `ANY_TEXTURE` to bias ops toward texture storage. However, `try_constrain_with_arg_repset` has a packed-dim compatibility check that requires ALL of the source repset's PDIs to exist in the output repset. `ANY_TEXTURE` has 3 texture layouts (WP, HP, CP) but `CONTIGUOUS_ANY` outputs only support WP, so the check fails and the texture bias is silently dropped. Without the bias, buffer storage cascades from ops that must use buffer (e.g. embedding with vocab exceeding texture limits) into downstream ops that could use texture, causing unnecessary buffer↔texture transitions. Fix: check PDI compatibility against the intersection of arg and source repsets (what would actually be applied) rather than the raw source. The intersection of `ANY_TEXTURE ∩ CONTIGUOUS_ANY` = `WIDTH_PACKED_TEXTURE`, which IS compatible with the output. Authored by Claude. ghstack-source-id: 364280901 @exported-using-ghexport Differential Revision: [D100004702](https://our.internmc.facebook.com/intern/diff/D100004702/)
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18779
Note: Links to docs will display an error until the docs builds have been completed. ⏳ No Failures, 37 PendingAs of commit 82044eb with merge base 4afd7f9 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
Pull Request resolved: #18771 When the same tensor is consumed by multiple ops that need a different storage representation, the pass previously inserted a separate clone transition for each consumer. Now it caches transition clones keyed by (source_node, target_storage_type, target_layout) and reuses existing clones when the same transition is needed again. For Qwen3 0.6B (8da4w fp16), the embedding output (BUFFER due to vocab_size exceeding texture limits) feeds both rms_norm and add which need TEXTURE. Previously 2 clones were inserted; now 1 clone is shared. Authored by Claude. ghstack-source-id: 364280900 @exported-using-ghexport Differential Revision: [D100004700](https://our.internmc.facebook.com/intern/diff/D100004700/)
SS-JIA
approved these changes
Apr 8, 2026
This file contains hidden or 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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #18770 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/516/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/516/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/main
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/516/orig
Differential Revision: D100004702
@diff-train-skip-merge