Skip to content

Actions: microsoft/onnxruntime

Actions

Windows GPU TensorRT CI Pipeline

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
windows_tensorrt.yml
7,606 workflow runs
7,606 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[webgpu] Fix the wrong fallback in Attention Windows GPU TensorRT CI Pipeline #8208: Pull request #26608 opened by qjia7
1h 55m 24s fix_attention
fix_attention
1h 55m 24s
Linux device discovery for TRT-RTX Ep Windows GPU TensorRT CI Pipeline #8207: Pull request #26210 synchronize by theHamsta
Action required theHamsta:sseitz/linux-device-discovery
theHamsta:sseitz/linux-device-discovery
Action required
[webgpu] Fused CopyKVCache and SplitPackedQKVWithRotaryEmbedding as SplitPackedQKVWithRotaryEmbeddingAndCopyKV Windows GPU TensorRT CI Pipeline #8206: Pull request #26563 synchronize by xiaofeihan1
1h 58m 55s xiaofeihan1:xiaofeihan/vec4_RoPE
xiaofeihan1:xiaofeihan/vec4_RoPE
1h 58m 55s
[AIX]Blocking the call of dladdr under _AIX Windows GPU TensorRT CI Pipeline #8205: Pull request #26513 synchronize by ranjitshs
Action required ranjitshs:aix-dladdr-fix
ranjitshs:aix-dladdr-fix
Action required
[QNN EP] Skip inputs/outputs shape validation for QNN Batch Multiple Windows GPU TensorRT CI Pipeline #8204: 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
[DML EP] Restrict MatMul to 4D Windows GPU TensorRT CI Pipeline #8203: Pull request #26583 synchronize by fdwr
2h 13m 9s user/dwayner/DmlEpMatMulRestrictTo4D
user/dwayner/DmlEpMatMulRestrictTo4D
2h 13m 9s
[build] fix packaging pipeline for arm64/linux (#26592) Windows GPU TensorRT CI Pipeline #8202: Commit 1851b73 pushed by fs-eire
2h 36m 0s main
main
2h 36m 0s
[QNN EP] Skip inputs/outputs shape validation for QNN Batch Multiple Windows GPU TensorRT CI Pipeline #8201: 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] Skip inputs/outputs shape validation for QNN Batch Multiple Windows GPU TensorRT CI Pipeline #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] Skip inputs/outputs shape validation for QNN Batch Multiple Windows GPU TensorRT CI Pipeline #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
Attenion(23) CUDA Windows GPU TensorRT CI Pipeline #8198: Pull request #26466 synchronize by titaiwangms
34m 9s titaiwang/support_attention_cuda
titaiwang/support_attention_cuda
34m 9s
Upgrade cpuinfo version and update some CPU feature detection code Windows GPU TensorRT CI Pipeline #8197: Pull request #26598 synchronize by edgchen1
1h 58m 56s edgchen1/update_cpuinfo_and_windows_arm_feature_checks
edgchen1/update_cpuinfo_and_windows_arm_feature_checks
1h 58m 56s
[webgpu] Throw errors for graph catpure when not implemented Windows GPU TensorRT CI Pipeline #8196: Pull request #26604 synchronize by qjia7
3h 47m 34s disable_non_fa_for_graph
disable_non_fa_for_graph
3h 47m 34s
[webgpu] Optimize Conv by im2col-matmul Windows GPU TensorRT CI Pipeline #8195: Pull request #26603 opened by daijh
Action required daijh:im2col-matmul
daijh:im2col-matmul
Action required
[webgpu] update ComputeContext to make it work with PrePack Windows GPU TensorRT CI Pipeline #8194: Pull request #26602 opened by fs-eire
30m 44s fs-eire/ex-compute-context
fs-eire/ex-compute-context
30m 44s
[webgpu] add support of output_qk for MHA (#26553) Windows GPU TensorRT CI Pipeline #8193: Commit 91a9d02 pushed by fs-eire
3h 17m 28s main
main
3h 17m 28s
[webgpu] Fused CopyKVCache and SplitPackedQKVWithRotaryEmbedding as SplitPackedQKVWithRotaryEmbeddingAndCopyKV Windows GPU TensorRT CI Pipeline #8192: Pull request #26563 synchronize by xiaofeihan1
2h 50m 45s xiaofeihan1:xiaofeihan/vec4_RoPE
xiaofeihan1:xiaofeihan/vec4_RoPE
2h 50m 45s
[webgpu] Fused CopyKVCache and SplitPackedQKVWithRotaryEmbedding as SplitPackedQKVWithRotaryEmbeddingAndCopyKV Windows GPU TensorRT CI Pipeline #8191: Pull request #26563 synchronize by xiaofeihan1
5m 14s xiaofeihan1:xiaofeihan/vec4_RoPE
xiaofeihan1:xiaofeihan/vec4_RoPE
5m 14s
Add partial data propagation to enhance shape inference Windows GPU TensorRT CI Pipeline #8190: Pull request #26269 synchronize by chilo-ms
44m 17s chi/fix_shape_inference
chi/fix_shape_inference
44m 17s
[VitisAI] Remove unused function body handling in graph fusion (#26519) Windows GPU TensorRT CI Pipeline #8189: Commit 8ac5670 pushed by yuslepukhin
2h 17m 44s main
main
2h 17m 44s
[QNN EP] Enable v81 devices (#26341) Windows GPU TensorRT CI Pipeline #8188: Commit afcdd2b pushed by edgchen1
49m 40s main
main
49m 40s
Attenion(23) CUDA Windows GPU TensorRT CI Pipeline #8187: Pull request #26466 synchronize by titaiwangms
34m 31s titaiwang/support_attention_cuda
titaiwang/support_attention_cuda
34m 31s
Upgrade cpuinfo version and update some CPU feature detection code Windows GPU TensorRT CI Pipeline #8186: Pull request #26598 synchronize by edgchen1
2h 8m 5s edgchen1/update_cpuinfo_and_windows_arm_feature_checks
edgchen1/update_cpuinfo_and_windows_arm_feature_checks
2h 8m 5s
Bump js-yaml in /js/react_native/e2e (#26593) Windows GPU TensorRT CI Pipeline #8185: Commit 32d4645 pushed by fs-eire
2h 6m 4s main
main
2h 6m 4s
[QNN EP] Fix Clip op with min or max from QDQ Windows GPU TensorRT CI Pipeline #8184: Pull request #26601 opened by qti-yuduo
Action required CodeLinaro:dev/yuduo/clip-qdq-minmax
CodeLinaro:dev/yuduo/clip-qdq-minmax
Action required