Repository navigation
Qualcomm AI Engine Direct - Cast an int64 get_attr right before its first user - #24046
Open
msluszniak wants to merge 1 commit into
Open
msluszniak wants to merge 1 commit into
msluszniak wants to merge 1 commit into
Conversation
…irst user create_const_node puts a get_attr ahead of the graph inputs, and I64toI32 inserted its int32 cast right after it. lift_constant_tensor_pass then turns the get_attr into a placeholder after the inputs, leaving the cast ahead of its argument, and lowering fails with "used before it has been defined". Hit by an int64 remainder by a scalar (YOLO26's top-k labels) in fp16.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24046
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New FailuresAs of commit 0d118e0 with merge base e6cfbf8 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
executorch-triage
Bot
added
the
community: contribution
nil-is-all
added
partner: qualcomm
This branch has not been deployed
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
3 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
I64toI32inserts the int32 cast of an int64get_attrright after it, butcreate_const_nodeputs thatget_attrabove the graph inputs.lift_constant_tensor_passthen turns it into a placeholder after the inputs, leaving the cast ahead of its argument: "used before it has been defined". The cast now goes right before the first user. Hit by an int64 remainder by a scalar (YOLO26's top-k labels) in fp16.Test plan
New
constant_cast_ordersubtest oftest_i64_to_i32fails on main and passes here; no other result inrework/passes/test.pychanges.cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin @abhinaykukkadapu @psiddh @nil-is-all