feat: add IsInf op builder to QNN EP#403
Draft
qti-yuduo wants to merge 1 commit into
Draft
Conversation
Maps ONNX IsInf -> QNN_OP_IS_INF, wiring the detect_positive and detect_negative ONNX attributes (default 1) to the corresponding QNN_DATATYPE_BOOL_8 scalar params. Without this, models containing IsInf (typically emitted by torch.nan_to_num decompositions) fall back to CPU and shatter the single-graph requirement of qnn_context_binary compilation. Validates input is FP32/FP16 and output is BOOL_8 per the QNN op contract.
qti-yuduo
requested review from
qti-ashwshan,
qti-chuteng,
qti-jkilpatrick,
qti-kromero,
tirupath-qti and
yath1
as code owners
Contributor
Diff Coverage |
yath1
approved these changes
May 19, 2026
|
|
||
| #if defined(__aarch64__) || defined(_M_ARM64) || defined(__linux__) | ||
|
|
||
| // HTP supports IsInf only in FP16 mode (per QAIRT HtpOpDefSupplement). The |
Collaborator
There was a problem hiding this comment.
Nit: HTP supports both in FP16 and FP32. Maybe we can add the same test for FP32 as well?
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Maps ONNX IsInf -> QNN_OP_IS_INF, wiring the detect_positive and detect_negative ONNX attributes (default 1) to the corresponding QNN_DATATYPE_BOOL_8 scalar params. Without this, models containing IsInf (typically emitted by torch.nan_to_num decompositions) fall back to CPU and shatter the single-graph requirement of qnn_context_binary compilation.
Validates input is FP32/FP16 and output is BOOL_8 per the QNN op contract.