Skip to content

Actions: microsoft/onnxruntime

Actions

ONNX Runtime DirectML Builds

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
windows_dml.yml
7,604 workflow runs
7,604 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

KFI-203 Improve thread safety of packing in convolve_kleidiai.cpp ONNX Runtime DirectML Builds #8205: Pull request #26575 reopened by hariharans29
In progress Colm-in-Arm:KFI-203
Colm-in-Arm:KFI-203
In progress
KFI-203 Improve thread safety of packing in convolve_kleidiai.cpp ONNX Runtime DirectML Builds #8204: Pull request #26575 reopened by hariharans29
37m 56s Colm-in-Arm:KFI-203
Colm-in-Arm:KFI-203
37m 56s
Upgrade cpuinfo version. Update ARM64 Windows feature detection to use cpuinfo functions which are now implemented. ONNX Runtime DirectML Builds #8203: Pull request #26598 opened by edgchen1
10m 10s edgchen1/update_cpuinfo_and_windows_arm_feature_checks
edgchen1/update_cpuinfo_and_windows_arm_feature_checks
10m 10s
Create a CUDA based memory arena instead of Cuda Allocator wrapped into BFCArena ONNX Runtime DirectML Builds #8202: Pull request #26535 reopened by yuslepukhin
1h 28m 56s yuslepukhin/cuda_pool_arena
yuslepukhin/cuda_pool_arena
1h 28m 56s
[QNN-EP] Enable verbose and artifacts saving in onnxruntime_provider_test.exe ONNX Runtime DirectML Builds #8201: Pull request #26396 synchronize by qti-hungjuiw
Action required CodeLinaro:dev/qti-hungjuiw/qnn-test-save
CodeLinaro:dev/qti-hungjuiw/qnn-test-save
Action required
[QNN EP] Relax checkShape for Batch Multiplier ONNX Runtime DirectML Builds #8200: Pull request #26336 synchronize by chunghow-qti
Action required CodeLinaro:dev/chunghow-qti/relax-shape-check
CodeLinaro:dev/chunghow-qti/relax-shape-check
Action required
[QNN EP] Relax checkShape for Batch Multiplier ONNX Runtime DirectML Builds #8199: Pull request #26336 synchronize by chunghow-qti
Action required CodeLinaro:dev/chunghow-qti/relax-shape-check
CodeLinaro:dev/chunghow-qti/relax-shape-check
Action required
Add weight layout transformation cache for Conv operator ONNX Runtime DirectML Builds #8198: Pull request #26595 synchronize by jchen10
Action required jchen10:conv_weight
jchen10:conv_weight
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8197: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8196: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8195: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8194: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8193: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8192: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8191: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8190: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[ARM CPU] SVE support for Sgemm kernel ONNX Runtime DirectML Builds #8189: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[build] fix packaging pipeline for arm64/linux ONNX Runtime DirectML Builds #8188: Pull request #26592 synchronize by fs-eire
1h 35m 59s fs-eire/fix-arm64-packaging-pipeline
fs-eire/fix-arm64-packaging-pipeline
1h 35m 59s
Add weight layout transformation cache for Conv operator ONNX Runtime DirectML Builds #8187: Pull request #26595 opened by jchen10
Action required jchen10:conv_weight
jchen10:conv_weight
Action required
[WebGPU] Register DataTransfer to Env ONNX Runtime DirectML Builds #8186: Pull request #26450 synchronize by qjia7
1h 35m 9s data_transfer_mgr
data_transfer_mgr
1h 35m 9s
Add int8 support to ConvInteger ONNX Runtime DirectML Builds #8185: Pull request #26585 synchronize by rivkastroh
Action required rivkastroh:implementation_ConvInteger
rivkastroh:implementation_ConvInteger
Action required
[webgpu] Fused CopyKVCache and SplitPackedQKVWithRotaryEmbedding as SplitPackedQKVWithRotaryEmbeddingAndCopyKV ONNX Runtime DirectML Builds #8184: Pull request #26563 synchronize by xiaofeihan1
1h 34m 18s xiaofeihan1:xiaofeihan/vec4_RoPE
xiaofeihan1:xiaofeihan/vec4_RoPE
1h 34m 18s
[webgpu] Fused CopyKVCache and SplitPackedQKVWithRotaryEmbedding as SplitPackedQKVWithRotaryEmbeddingAndCopyKV ONNX Runtime DirectML Builds #8183: Pull request #26563 synchronize by xiaofeihan1
11m 59s xiaofeihan1:xiaofeihan/vec4_RoPE
xiaofeihan1:xiaofeihan/vec4_RoPE
11m 59s
Integration with ONNX==1.20.0 ONNX Runtime DirectML Builds #8182: Pull request #26579 synchronize by titaiwangms
1h 30m 39s titaiwang/check_onnx_1_20
titaiwang/check_onnx_1_20
1h 30m 39s
Integration with ONNX==1.20.0 ONNX Runtime DirectML Builds #8181: Pull request #26579 synchronize by titaiwangms
1h 6m 25s titaiwang/check_onnx_1_20
titaiwang/check_onnx_1_20
1h 6m 25s