saymrwulf/onnxruntime
1
0
Fork 0
mirror of https://github.com/saymrwulf/onnxruntime.git synced 2026-05-18 21:21:17 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
onnxruntime/onnxruntime/test
History
wejoncy 86870114eb
[CoreML] support coreml model cache (#23065) 
### Description
Refactor compute plan profiling

Support cache coreml model to speed up session initialization. this is
only support by user provided entry and user responsible to manage the
cache


With the cache, session initialization time can be reduced by 50% or
more:
|model| before| after|
|--|--|--|
|yolo11.onnx| 0.6s|0.1s|
|yolo11-fp16.onnx|1.8s|0.1s|


### Motivation and Context
<!-- - Why is this change required? What problem does it solve?
- If it fixes an open issue, please link to the issue here. -->

---------

Co-authored-by: wejoncy <wejoncy@.com>
Co-authored-by: Scott McKay <skottmckay@gmail.com>
2024-12-31 09:29:41 +08:00
..
common Revert DML pipeline changes (#23135) 2024-12-18 10:42:10 -08:00
contrib_ops Integrate onnx 1.17.0 (#21897) 2024-12-24 09:02:02 -08:00
cuda_host Enable CUDA EP unit testing on Windows (#20039) 2024-03-27 13:32:36 -07:00
custom_op_registration
debug_node_inputs_outputs Delete path.h (#21211) 2024-07-04 15:54:13 +08:00
flatbuffers Enablement of onnxruntime for AIX and fixing issues related to big-endian platform. (#21133) 2024-07-17 12:37:06 -07:00
framework Implement pre-packed blobs serialization on disk and their memory mapping on load (#23069) 2024-12-20 10:49:08 -08:00
fuzzing [Fuzzer] Add two new ORT libfuzzer (Linux clang support for now) (#22055) 2024-09-12 11:50:34 -07:00
global_thread_pools Remove references to the outdated CUDA EP factory method (#21549) 2024-07-29 21:59:16 -07:00
ir Fix typos according to reviewdog report. (#21335) 2024-07-22 13:37:32 -07:00
logging_apis Specify iOS simulator runtime version (#22474) 2024-10-18 09:26:06 -07:00
lora Revert DML pipeline changes (#23135) 2024-12-18 10:42:10 -08:00
mlas [ARM CPU] Add rotary embedding fp16 kernel (#23013) 2024-12-06 13:25:48 -08:00
onnx Integrate onnx 1.17.0 (#21897) 2024-12-24 09:02:02 -08:00
opaque_api
optimizer Reduce default logger usage (#23030) 2024-12-10 12:54:14 +11:00
perftest [CoreML] support coreml model cache (#23065) 2024-12-31 09:29:41 +08:00
platform [CoreML] Create EP by AppendExecutionProvider (#22675) 2024-11-27 09:26:31 +08:00
proto
providers [CoreML] support coreml model cache (#23065) 2024-12-31 09:29:41 +08:00
python Integrate onnx 1.17.0 (#21897) 2024-12-24 09:02:02 -08:00
qnn_ctx_gen Fix the ctx_gen tool to make sure all generated ctx.onnx have max_size (#23097) 2024-12-12 21:12:02 -08:00
quantization Disable CPU EP's allocator's arena when address sanitizer is enabled (#19485) 2024-02-12 09:39:49 -08:00
shared_lib Integrate onnx 1.17.0 (#21897) 2024-12-24 09:02:02 -08:00
testdata Integrate onnx 1.17.0 (#21897) 2024-12-24 09:02:02 -08:00
unittest_main Specify iOS simulator runtime version (#22474) 2024-10-18 09:26:06 -07:00
util Revert DML pipeline changes (#23135) 2024-12-18 10:42:10 -08:00
wasm [wasm/test] update packages versions (#23008) 2024-12-04 13:08:13 -08:00
webgpu fix webgpu delay load test (#23157) 2024-12-20 13:37:12 -08:00
win_getopt
xctest Specify iOS simulator runtime version (#22474) 2024-10-18 09:26:06 -07:00
run_benchmark.py Add onnxruntime/test/run_benchmark.py helper script. (#19234) 2024-04-05 07:02:01 -07:00
run_benchmark.readme.md Add onnxruntime/test/run_benchmark.py helper script. (#19234) 2024-04-05 07:02:01 -07:00