mirror of
https://github.com/saymrwulf/onnxruntime.git
synced 2026-05-18 21:21:17 +00:00
Add MultiHeadAttention for ROCm EP. **Before:** ``` 'engine': 'onnxruntime' 'version': '1.15.0' 'height': 512 'width': 512 'steps': 50 'batch_size': 1 'batch_count': 5 'num_prompts': 1 'average_latency': 3.878769588470459 'median_latency': 3.8792178630828857 'first_run_memory_MB': -1 'second_run_memory_MB': -1 'model_name': 'runwayml/stable-diffusion-v1-5' 'directory': './sd-v1-5-onnx-fp16-nomha' 'provider': 'ROCMExecutionProvider' 'disable_safety_checker': True ``` **After:** ``` 'engine': 'onnxruntime' 'version': '1.15.0' 'height': 512 'width': 512 'steps': 50 'batch_size': 1 'batch_count': 5 'num_prompts': 1 'average_latency': 2.364924430847168 'median_latency': 2.3650705814361572 'first_run_memory_MB': -1 'second_run_memory_MB': -1 'model_name': 'runwayml/stable-diffusion-v1-5' 'directory': './sd-v1-5-onnx-fp16' 'provider': 'ROCMExecutionProvider' 'disable_safety_checker': True ``` |
||
|---|---|---|
| .. | ||
| external | ||
| patches | ||
| tensorboard | ||
| adjust_global_compile_flags.cmake | ||
| CMakeLists.txt | ||
| CMakeSettings.json | ||
| codeconv.runsettings | ||
| deps.txt | ||
| EnableVisualStudioCodeAnalysis.props | ||
| gdk_toolchain.cmake | ||
| Info.plist.in | ||
| libonnxruntime.pc.cmake.in | ||
| nuget_helpers.cmake | ||
| onnxruntime.cmake | ||
| onnxruntime_codegen_tvm.cmake | ||
| onnxruntime_common.cmake | ||
| onnxruntime_config.h.in | ||
| onnxruntime_csharp.cmake | ||
| onnxruntime_flatbuffers.cmake | ||
| onnxruntime_framework.cmake | ||
| onnxruntime_fuzz_test.cmake | ||
| onnxruntime_graph.cmake | ||
| onnxruntime_ios.toolchain.cmake | ||
| onnxruntime_java.cmake | ||
| onnxruntime_java_unittests.cmake | ||
| onnxruntime_kernel_explorer.cmake | ||
| onnxruntime_language_interop_ops.cmake | ||
| onnxruntime_mlas.cmake | ||
| onnxruntime_nodejs.cmake | ||
| onnxruntime_objectivec.cmake | ||
| onnxruntime_opschema_lib.cmake | ||
| onnxruntime_optimizer.cmake | ||
| onnxruntime_providers.cmake | ||
| onnxruntime_pyop.cmake | ||
| onnxruntime_python.cmake | ||
| onnxruntime_rocm_hipify.cmake | ||
| onnxruntime_session.cmake | ||
| onnxruntime_snpe_provider.cmake | ||
| onnxruntime_training.cmake | ||
| onnxruntime_unittests.cmake | ||
| onnxruntime_util.cmake | ||
| onnxruntime_webassembly.cmake | ||
| precompiled_header.cmake | ||
| Sdl.ruleset | ||
| set_winapi_family_desktop.h | ||
| target_delayload.cmake | ||
| uwp_stubs.h | ||
| wcos_rules_override.cmake | ||
| winml.cmake | ||
| winml_cppwinrt.cmake | ||
| winml_sdk_helpers.cmake | ||
| winml_unittests.cmake | ||