onnxruntime/onnxruntime/test
Adrian Lizarraga 4838cb6b3e
[QNN Quantization] Ensure fused nodes have names (#19650)
### Description
- Updates the `qnn_preprocess_model()` method to set a name for any new
nodes added to the graph (due to fusion).
- Updates the `qnn_preprocess_model()` method to set a name for any
unnamed nodes that previously existed in the original graph.
- Adds unit tests for fusions (previously missing)
  - Checks that fused node names exist and are unique
  - Checks that fused graph is equivalent to original graph


### Motivation and Context
Nodes are not strictly required to have names. However, a
planned/upcoming feature to support mixed-precision (integer) quantized
models needs nodes to have names.
2024-02-27 02:27:35 -08:00
..
common ORT ETW dynamic logging that improves ORT diagnosability & performance (#18882) 2024-01-11 12:43:27 -08:00
contrib_ops ONNX Gelu Op in Opset 20 (#19560) 2024-02-23 11:05:16 +08:00
custom_op_registration
debug_node_inputs_outputs
framework Introduce reused_buffer_index_per_stream in allocation planner which will be reset after computing the reuse buffer for each stream (#19515) 2024-02-22 10:19:08 -08:00
fuzzing
global_thread_pools Replace T4 to A10 in Linux GPU workflow (#19205) 2024-01-23 10:49:24 -08:00
ir Make session configuration options available to kernels via OpKernelInfo (#18897) 2024-01-13 10:02:43 +10:00
logging_apis Remove two tests from test_logging_apis.cc (#19100) 2024-01-12 09:26:28 -08:00
mlas [MLAS AArch64] SQNBitGemm optimization (#19272) 2024-01-30 14:29:12 -08:00
onnx ONNX Gelu Op in Opset 20 (#19560) 2024-02-23 11:05:16 +08:00
opaque_api
optimizer add GatherSliceToSplitFusion and Unittest (#19218) 2024-02-14 15:07:56 -08:00
perftest [DML EP] Enable DML Graph Serialization (#19505) 2024-02-26 11:35:13 -08:00
platform Add capturestate / rundown ETW support logging for session and provider options (#19397) 2024-02-08 11:28:05 -08:00
proto
providers Fix cuDNN v9 build by replacing removed cuDNN v6 RNN API usage by cuDNN v8 RNN API and reenable RNN tests for CUDA EP (#19419) 2024-02-23 08:45:17 -08:00
python [QNN Quantization] Ensure fused nodes have names (#19650) 2024-02-27 02:27:35 -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 [ROCm] enable hipGraph (#18382) 2024-01-23 11:17:04 +08:00
testdata Introduce reused_buffer_index_per_stream in allocation planner which will be reset after computing the reuse buffer for each stream (#19515) 2024-02-22 10:19:08 -08:00
unittest_main Disable a few tests for wasm build (#19316) 2024-01-30 08:16:57 -08:00
util Add support for NHWC GridSample in the CUDA EP and enable grid_sample_test for all EPs (#19562) 2024-02-22 19:47:15 -08:00
wasm Bump follow-redirects from 1.15.2 to 1.15.4 in /onnxruntime/test/wasm (#19069) 2024-01-11 16:13:22 -08:00
win_getopt
xctest Enable backtrace in unit tests (#17655) 2023-09-29 12:32:56 -07:00