Repository navigation
Qualcomm AI Engine Direct - Leave constant-only partitions on CPU - #24051
Open
msluszniak wants to merge 1 commit into
Open
msluszniak wants to merge 1 commit into
msluszniak wants to merge 1 commit into
Conversation
A partition fed only by constants has no graph input, and QNN cannot build such a
graph ("No graph inputs present"). It happens when an int64 buffer's I64toI32 cast
is supported but the buffer's consumer is not, e.g. an index into a lookup table
with indices from an op left on CPU. Mutable buffers still count as runtime inputs.
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/24051
Note: Links to docs will display an error until the docs builds have been completed. ❌ 3 New Failures, 1 Unclassified FailureAs of commit 4507227 with merge base e6cfbf8 ( NEW FAILURES - The following jobs have failed:
UNCLASSIFIED FAILURE - DrCI could not classify the following job because the workflow did not run on the merge base. The failure may be pre-existing on trunk or introduced by this PR:
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
borys3kk
pushed a commit
to borys3kk/swm_executorch
that referenced
this pull request
Oct 22, 2026
A partition fed only by constants has no graph input, and QNN cannot build such a
graph ("No graph inputs present"). It happens when an int64 buffer's I64toI32 cast
is supported but the buffer's consumer is not, e.g. an index into a lookup table
with indices from an op left on CPU. Mutable buffers still count as runtime inputs.
Backport of pytorch/executorch#24051 (on top of the #23915 backport, whose orphaned-dequant filter runs first).
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
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
A partition fed only by constants has no graph input, so context binary generation fails with "No graph inputs present". It happens when an int64 buffer's
I64toI32cast is delegable but the buffer's consumer is not (e.g. a lookup table indexed by an op left on CPU). The partitioner now leaves such partitions on CPU; mutable buffers still count as runtime inputs.Test plan
New
test_passes.py::TestPasses::test_constant_only_partition_stays_on_cpufails on main and passes here.test_passes.py,rework/passes/test.pyand the x86-simulatorTestQNNFloatingPointOperator/TestQNNQuantizedOperatorsuites give the same results as main.cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin @abhinaykukkadapu @psiddh @nil-is-all