-
Notifications
You must be signed in to change notification settings - Fork 10
Pull requests: onnxruntime/onnxruntime-qnn
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[DO NOT MERGE] Pass int16 activations for matmulnbits op
#769
opened Aug 26, 2026 by
qti-ashwshan
Collaborator
•
Draft
[Docs] Split Compiled Model Encryption into its own top-level section
#768
opened Aug 26, 2026 by
tzuhsuanwei
Collaborator
Loading…
[QNN EP] Add ORT profiling timeline support
#767
opened Aug 26, 2026 by
kuanyul-qti
Collaborator
Loading…
Allow quantized uint8/int8 Conv on QNN CPU backend
#766
opened Aug 26, 2026 by
mantpand
Collaborator
Loading…
[QNN EP] Preserve symmetric U16 MatMul input encoding
#765
opened Aug 26, 2026 by
1duo
Contributor
Loading…
[CI] Redirect docker container TMPDIR to repo volume to fix ENOSPC
#759
opened Aug 24, 2026 by
huaychou
Collaborator
Loading…
[QNN EP] Refactor LPBQ lowering helpers across op builders
#755
opened Aug 24, 2026 by
qti-ashimaj
Collaborator
•
Draft
[OpBuilder] Allow op builder acquiring HTP arch.
#754
opened Aug 24, 2026 by
minfhong-qti
Collaborator
Loading…
[QNN EP] Expose htp_reused_io_limit_mb provider option for HTP AOT context load
#752
opened Aug 23, 2026 by
chunghow-qti
Collaborator
Loading…
1 of 2 tasks
[QNN] refactor group query attention setup
#751
opened Aug 22, 2026 by
qti-chuteng
Collaborator
Loading…
[QNN EP] Use QNN API Version instead of QNN SDK version
#749
opened Aug 20, 2026 by
qti-mbadnara
Collaborator
Loading…
[QNN_EP] Rewrite QKV split to remove 5D Ops.
#745
opened Aug 19, 2026 by
ankus-qti
Collaborator
Loading…
Fix shared bias used when act scales are different
#739
opened Aug 17, 2026 by
yath1
Collaborator
Loading…
[QNN-EP] Fix and re-enable SSRGraphExecuteEpContextWeightSharing
#732
opened Aug 14, 2026 by
qti-hungjuiw
Collaborator
•
Draft
[QNN] add arm64ec gate for HTP weight sharing
#731
opened Aug 14, 2026 by
qti-chuteng
Collaborator
Loading…
Add ORT arm64ec arch gate for GPU weight-sharing
#726
opened Aug 13, 2026 by
vjatoth-qti
Collaborator
Loading…
[QNNEP-LORA] Add support for Lora in ORT-QNNEP-LORA flow
#723
opened Aug 13, 2026 by
qti-akshjame
Collaborator
Loading…
[QNN EP] Add QDQ selector for GRU op to enable INT8 HTP execution
#721
opened Aug 13, 2026 by
yuhuchua-qti
Collaborator
•
Draft
2 of 4 tasks
[QNN EP] Reject FP16/FP32 Tensors on HTP runtime for v68
#708
opened Aug 8, 2026 by
qti-mbadnara
Collaborator
Loading…
DO NOT MERGE: Changes for testing mem alloc error on Android
#707
opened Aug 8, 2026 by
quic-calvnguy
Collaborator
•
Draft
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.