Skip to content

Actions: microsoft/onnxruntime

Actions

CUDA Plugin Windows CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
windows_cuda_plugin.yml
907 workflow runs
907 workflow runs

Filter by Event

⌥ + click/return to exclude

Filter by Status

⌥ + click/return to exclude

Filter by Branch

⌥ + click/return to exclude

Filter by Actor

⌥ + click/return to exclude
[CoreML EP] Add QuickGelu support CUDA Plugin Windows CI #923: Pull request #28184 synchronize by maxwbuckley
Action required maxwbuckley:coreml-quickgelu
maxwbuckley:coreml-quickgelu
Action required
webgpu: use naive reduction CUDA Plugin Windows CI #922: Pull request #28174 synchronize by xhcao
Action required xhcao:use-naive-reduction
xhcao:use-naive-reduction
Action required
[ARM CPU] SVE support for Sgemm kernel CUDA Plugin Windows CI #921: Pull request #26027 synchronize by akote123
Action required akote123:aruna/sgemm_sve
akote123:aruna/sgemm_sve
Action required
[CoreML EP] Add QuickGelu support CUDA Plugin Windows CI #920: Pull request #28184 synchronize by maxwbuckley
Action required maxwbuckley:coreml-quickgelu
maxwbuckley:coreml-quickgelu
Action required
[CoreML EP] Add QuickGelu support CUDA Plugin Windows CI #919: Pull request #28184 synchronize by maxwbuckley
Action required maxwbuckley:coreml-quickgelu
maxwbuckley:coreml-quickgelu
Action required
docs: add missing import os in FAQ.md Python code snippet CUDA Plugin Windows CI #918: Pull request #28220 opened by lingxiu58
Action required lingxiu58:fix/issue-28219-faq-missing-import-os
lingxiu58:fix/issue-28219-faq-missing-import-os
Action required
[CI] Remove win gpu doc gen and trt cuda mini CI pipelines CUDA Plugin Windows CI #917: Pull request #28218 opened by tianleiwu
1h 34m 5s tlwu/remove_doc_gen_and_trt_mini_pipeline
tlwu/remove_doc_gen_and_trt_mini_pipeline
1h 34m 5s
[CUDA] PagedAttention: add SM<80 fp16 fallback via memory-efficient attention CUDA Plugin Windows CI #916: Pull request #28200 synchronize by elwhyjay
Action required elwhyjay:feature/paged-attention-mea-fallback
elwhyjay:feature/paged-attention-mea-fallback
Action required
Add workflow to replace Windows GPU Doc Gen CI Pipeline (#28192) CUDA Plugin Windows CI #915: Commit 2ea847c pushed by tianleiwu
1h 36m 53s main
main
1h 36m 53s
[CUDA] PagedAttention: add SM<80 fp16 fallback via memory-efficient attention CUDA Plugin Windows CI #914: Pull request #28200 synchronize by elwhyjay
1h 36m 31s elwhyjay:feature/paged-attention-mea-fallback
elwhyjay:feature/paged-attention-mea-fallback
1h 36m 31s
fix: add missing BackendKernelSelectorConfig parameter to QNBitGemmPa… CUDA Plugin Windows CI #913: Commit 25d58f0 pushed by tianleiwu
1h 31m 54s main
main
1h 31m 54s
Add packaging pipeline for CUDA plugin EP CUDA Plugin Windows CI #912: Pull request #28152 synchronize by tianleiwu
1h 34m 1s tlwu/20260420/cuda_plugin_package_pipeline
tlwu/20260420/cuda_plugin_package_pipeline
1h 34m 1s
Add exponential-backoff option for thread pool spin loop (#28096) CUDA Plugin Windows CI #911: Commit 5743f71 pushed by tianleiwu
1h 32m 44s main
main
1h 32m 44s
[CUDA] PagedAttention: add SM<80 fp16 fallback via memory-efficient attention CUDA Plugin Windows CI #910: Pull request #28200 synchronize by elwhyjay
Action required elwhyjay:feature/paged-attention-mea-fallback
elwhyjay:feature/paged-attention-mea-fallback
Action required
Implement CUDA EP Plugin profiling API CUDA Plugin Windows CI #909: Pull request #28216 synchronize by yuslepukhin
1h 34m 43s yuslepukhin/cuda_ep_plugin_profiling
yuslepukhin/cuda_ep_plugin_profiling
1h 34m 43s
Bound total output allocation size in Tile kernel CUDA Plugin Windows CI #908: Pull request #28070 synchronize by GopalakrishnanN
1h 23m 35s FixTile-repeats-dos-CVE
FixTile-repeats-dos-CVE
1h 23m 35s
ICM fixes (5/n) CUDA Plugin Windows CI #907: Pull request #27971 synchronize by hariharans29
1h 27m 13s hari/icm_5
hari/icm_5
1h 27m 13s
ICM fixes (5/n) CUDA Plugin Windows CI #906: Pull request #27971 synchronize by hariharans29
14s hari/icm_5
hari/icm_5
14s
ICM fixes (5/n) CUDA Plugin Windows CI #905: Pull request #27971 synchronize by hariharans29
17s hari/icm_5
hari/icm_5
17s
ICM fixes (5/n) CUDA Plugin Windows CI #904: Pull request #27971 synchronize by hariharans29
13s hari/icm_5
hari/icm_5
13s
ICM fixes (5/n) CUDA Plugin Windows CI #903: Pull request #27971 synchronize by hariharans29
15s hari/icm_5
hari/icm_5
15s
ICM fixes (5/n) CUDA Plugin Windows CI #902: Pull request #27971 synchronize by hariharans29
12m 44s hari/icm_5
hari/icm_5
12m 44s
[Core] Add correctness tests for SpaceToDepth and MobileClip Attentio… CUDA Plugin Windows CI #901: Commit f38dec1 pushed by hariharans29
1h 21m 51s main
main
1h 21m 51s
ONNX Attention CUDA: MEA decode, unfused softcap, spec-correct ordering, and NaN fix CUDA Plugin Windows CI #900: Pull request #27992 synchronize by titaiwangms
1h 22m 9s titaiwangms:feature/mea-decode-support-v2
titaiwangms:feature/mea-decode-support-v2
1h 22m 9s
ICM fixes (5/n) CUDA Plugin Windows CI #899: Pull request #27971 synchronize by hariharans29
13m 42s hari/icm_5
hari/icm_5
13m 42s