onnxruntime
[QNN EP] Reduce overhead of QNN context binary loading
#17965
Merged

[QNN EP] Reduce overhead of QNN context binary loading #17965

HectorSVC merged 6 commits into main from qnn_cache_overhead
HectorSVC
HectorSVC Avoid string copy for the QNN context binary
d9bf69ea
HectorSVC Update the QNN context loading to avoid extra string buffer copy
2d5018f5
HectorSVC HectorSVC requested a review from adrianlizarraga adrianlizarraga 2 years ago
HectorSVC HectorSVC requested a review from jywu-msft jywu-msft 2 years ago
HectorSVC revert changes unrelated
c9a13b6f
HectorSVC Fix UT failure
d5ec44c6
HectorSVC Merge branch 'main' into qnn_cache_overhead
7ee58e2a
HectorSVC remove qnn_cache_model_handler_.reset(); from Compile in case there c…
ff40a218
jywu-msft
jywu-msft approved these changes on 2023-10-18
HectorSVC HectorSVC merged 35ecce45 into main 2 years ago
HectorSVC HectorSVC deleted the qnn_cache_overhead branch 2 years ago

Login to write a write a comment.

Login via GitHub

Assignees
No one assigned
Labels
Milestone