Skip to content

Actions: microsoft/onnxruntime

Actions

ONNX Runtime DirectML Builds

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
windows_dml.yml
7,767 workflow runs
7,767 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[webgpu] Correct definition of large numbers, fixes softmax(max_negative_number) in float32 ONNX Runtime DirectML Builds #8411: Pull request #26670 synchronize by xenova
Action required xenova:webgpu-Softmax-fix
xenova:webgpu-Softmax-fix
Action required
[webgpu] Support int64 for range ONNX Runtime DirectML Builds #8410: Pull request #26673 opened by qjia7
1h 35m 9s range
range
1h 35m 9s
[OVEP] OpenVINO EP Features and bug-fixes for ORT-1.24 ONNX Runtime DirectML Builds #8409: Pull request #26672 synchronize by preetha-intel
Action required intel:ovep-1.24
intel:ovep-1.24
Action required
[OVEP] OpenVINO EP Features and bug-fixes for ORT-1.24 ONNX Runtime DirectML Builds #8408: Pull request #26672 opened by preetha-intel
Action required intel:ovep-1.24
intel:ovep-1.24
Action required
Expose start profiling API ONNX Runtime DirectML Builds #8407: Pull request #26652 synchronize by xiaofeihan1
1h 25m 47s xiaofeihan1:xiaofeihan/add_start_profiling
xiaofeihan1:xiaofeihan/add_start_profiling
1h 25m 47s
[webgpu] Optimize Conv by im2col-matmul ONNX Runtime DirectML Builds #8406: Pull request #26603 synchronize by daijh
Action required daijh:im2col-matmul
daijh:im2col-matmul
Action required
Fix missing include for CudaHasBF16Support in conv_fp16_test.cc ONNX Runtime DirectML Builds #8405: Pull request #26671 synchronize by Copilot AI
1h 31m 55s copilot/fix-cuda-bf16-support-error
copilot/fix-cuda-bf16-support-error
1h 31m 55s
Fix missing include for CudaHasBF16Support in conv_fp16_test.cc ONNX Runtime DirectML Builds #8404: Pull request #26671 opened by Copilot AI
Action required copilot/fix-cuda-bf16-support-error
copilot/fix-cuda-bf16-support-error
Action required
[webgpu] Optimize Conv by im2col-matmul ONNX Runtime DirectML Builds #8403: Pull request #26603 synchronize by daijh
1h 33m 51s daijh:im2col-matmul
daijh:im2col-matmul
1h 33m 51s
[webgpu] Use multiplication instead of pow if exponent is 2 (#26667) ONNX Runtime DirectML Builds #8402: Commit 4c43c66 pushed by guschmue
1h 24m 52s main
main
1h 24m 52s
[webgpu] Optimize Conv by im2col-matmul ONNX Runtime DirectML Builds #8401: Pull request #26603 synchronize by daijh
1h 4m 58s daijh:im2col-matmul
daijh:im2col-matmul
1h 4m 58s
[webgpu] Correct definition of large numbers, fixes softmax(max_negative_number) in float32 ONNX Runtime DirectML Builds #8400: Pull request #26670 opened by xenova
Action required xenova:webgpu-Softmax-fix
xenova:webgpu-Softmax-fix
Action required
[OVEP] Update OV version to 2025.3.0 ONNX Runtime DirectML Builds #8399: Pull request #26556 reopened by edgchen1
1h 26m 44s intel:jatin_update_ci_version_2025_3
intel:jatin_update_ci_version_2025_3
1h 26m 44s
Add MlasIsDynamicQGemmAvailable() helper and use that in place of platform-specific checks ONNX Runtime DirectML Builds #8398: Pull request #26668 synchronize by edgchen1
1h 25m 27s edgchen1/mlas_is_dynamic_qgemm_available
edgchen1/mlas_is_dynamic_qgemm_available
1h 25m 27s
Upgrade cpuinfo version and update some CPU feature detection code ONNX Runtime DirectML Builds #8397: Pull request #26598 synchronize by edgchen1
1h 36m 31s edgchen1/update_cpuinfo_and_windows_arm_feature_checks
edgchen1/update_cpuinfo_and_windows_arm_feature_checks
1h 36m 31s
Add MlasIsDynamicQGemmAvailable() helper and use that in place of platform-specific checks ONNX Runtime DirectML Builds #8396: Pull request #26668 opened by edgchen1
1h 33m 12s edgchen1/mlas_is_dynamic_qgemm_available
edgchen1/mlas_is_dynamic_qgemm_available
1h 33m 12s
[webgpu] Use multiplication instead of pow if exponent is 2 ONNX Runtime DirectML Builds #8395: Pull request #26667 opened by xenova
1h 32m 36s xenova:webgpu-Pow-fix
xenova:webgpu-Pow-fix
1h 32m 36s
Integration with ONNX==1.20.0 ONNX Runtime DirectML Builds #8394: Pull request #26579 synchronize by titaiwangms
1h 34m 52s titaiwang/check_onnx_1_20
titaiwang/check_onnx_1_20
1h 34m 52s
Integration with ONNX==1.20.0 ONNX Runtime DirectML Builds #8393: Pull request #26579 synchronize by titaiwangms
42m 47s titaiwang/check_onnx_1_20
titaiwang/check_onnx_1_20
42m 47s
ARM KleidiAI Micro-Kernel: Depthwise Convolution (3x3 kernel, Stride of 1) ONNX Runtime DirectML Builds #8392: Pull request #26654 synchronize by damdoo01-arm
Action required damdoo01-arm:depthwise_conv_3x3_s1_updated
damdoo01-arm:depthwise_conv_3x3_s1_updated
Action required
[QNN-EP] Enable verbose and artifacts saving in onnxruntime_provider_… ONNX Runtime DirectML Builds #8391: Commit f02a640 pushed by edgchen1
1h 32m 29s main
main
1h 32m 29s
[webgpu] Fix bug introduced by RoE (#26661) ONNX Runtime DirectML Builds #8390: Commit 55bfa30 pushed by guschmue
1h 32m 19s main
main
1h 32m 19s
Rework the mechanism for checking SME capabilities ONNX Runtime DirectML Builds #8389: Pull request #26666 opened by JonathanC-ARM
36m 9s JonathanC-ARM:jclohess_sme_detection_struct
JonathanC-ARM:jclohess_sme_detection_struct
36m 9s
[webgpu] Remove global_id and workgroup_id in gemm_utils.cc ONNX Runtime DirectML Builds #8388: Pull request #26662 synchronize by Jiawei-Shao
1h 22m 49s Jiawei-Shao:fix-global-id-workgroup-id
Jiawei-Shao:fix-global-id-workgroup-id
1h 22m 49s
[webgpu] Remove global_id and workgroup_id in gemm_utils.cc ONNX Runtime DirectML Builds #8387: Pull request #26662 synchronize by Jiawei-Shao
Action required Jiawei-Shao:fix-global-id-workgroup-id
Jiawei-Shao:fix-global-id-workgroup-id
Action required