Xavier Dupré 80213a9e66 Add implementation for ScatterND (#19540) ... ### Description onnxruntime switches to CPU for ScatterND after opset 13. This extends the implementation of higher opsets.		2024-04-24 14:08:50 +02:00
..
common
contrib_ops	[DML EP] Add MatMulNBits (#20308)	2024-04-19 15:05:37 -07:00
cuda_host
custom_op_registration
debug_node_inputs_outputs
flatbuffers	Support >2GB of Tensor data in training checkpoint (#20077)	2024-04-22 15:17:43 -07:00
framework	Avoid call to Node::ToProto on first Graph::Resolve to improve session creation performance. (#20296)	2024-04-17 10:07:12 +10:00
fuzzing
global_thread_pools
ir	Introduce memory efficient topological sort (#20258)	2024-04-23 08:00:23 +08:00
logging_apis
mlas	[MLAS][AArch64] SQNBitGemm M>1 CompFp32 kernel optimization (#20319)	2024-04-17 17:50:26 -07:00
onnx	Enable provider option to let user provider the profiling file path (#20285)	2024-04-17 09:42:40 -07:00
opaque_api
optimizer
perftest	OVEP Bug fix 1.18 (#20408)	2024-04-22 18:31:05 -07:00
platform	Add helper to get errno and error message (#20324)	2024-04-17 21:17:36 +10:00
proto
providers	Add implementation for ScatterND (#19540)	2024-04-24 14:08:50 +02:00
python	Add implementation for ScatterND (#19540)	2024-04-24 14:08:50 +02:00
quantization
shared_lib	fix android build issue (#20389)	2024-04-19 14:21:34 -07:00
testdata	Fix handling of nodes that get assigned to kMSInternalNHWCDomain when loading an ORT format model. (#20379)	2024-04-22 18:34:01 -07:00
unittest_main
util	[DML EP] Add graph capture (#20257)	2024-04-18 10:15:00 -07:00
wasm
win_getopt
xctest
run_benchmark.py
run_benchmark.readme.md