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
6,965 workflow runs
6,965 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[EP API] Check for out-of-range node in EpGraph::IndexToEpNodeMap::GetEpNode Windows GPU TensorRT CI Pipeline #7445: Pull request #26373 opened by minfhong-qti
Action required CodeLinaro:dev/minfhong/fix-epnode-getepnode
CodeLinaro:dev/minfhong/fix-epnode-getepnode
Action required
[webgpu] Simplify copyKVCache Windows GPU TensorRT CI Pipeline #7444: Pull request #26371 synchronize by qjia7
1h 44m 20s fix_copy_kv_cache
fix_copy_kv_cache
1h 44m 20s
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7443: Pull request #26349 reopened by tianleiwu
1h 43m 56s tlwu/cuda130
tlwu/cuda130
1h 43m 56s
[CANN] Fix the ACL_ERROR_REPEAT_INITIALIZE error that occurs when coexisting… Windows GPU TensorRT CI Pipeline #7442: Pull request #26193 synchronize by bachelor-dou
Action required bachelor-dou:update
bachelor-dou:update
Action required
use std::move(model_proto) to avoid extra copy Windows GPU TensorRT CI Pipeline #7441: Pull request #26372 opened by mingyueliuh
Action required mingyueliuh:optimize-model-construct
mingyueliuh:optimize-model-construct
Action required
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7440: Pull request #26349 synchronize by tianleiwu
1h 44m 20s tlwu/cuda130
tlwu/cuda130
1h 44m 20s
[webgpu] Simplify copyKVCache Windows GPU TensorRT CI Pipeline #7439: Pull request #26371 opened by qjia7
1h 45m 0s fix_copy_kv_cache
fix_copy_kv_cache
1h 45m 0s
Bump actions/setup-node from 5 to 6 (#26357) Windows GPU TensorRT CI Pipeline #7438: Commit ae71a57 pushed by snnn
1h 46m 51s main
main
1h 46m 51s
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7437: Pull request #26349 synchronize by tianleiwu
45m 39s tlwu/cuda130
tlwu/cuda130
45m 39s
Bump vite from 6.3.6 to 6.4.1 in /js/web/test/e2e/exports/testcases/vite-default Windows GPU TensorRT CI Pipeline #7436: Pull request #26370 opened by dependabot bot
2h 0m 43s dependabot/npm_and_yarn/js/web/test/e2e/exports/testcases/vite-default/vite-6.4.1
dependabot/npm_and_yarn/js/web/test/e2e/exports/testcases/vite-default/vite-6.4.1
2h 0m 43s
[web] support JSPI build (#26095) Windows GPU TensorRT CI Pipeline #7435: Commit 6efb844 pushed by fs-eire
1h 3m 19s main
main
1h 3m 19s
[QNN-EP] Enable Optrace from QNN into QNN EP Windows GPU TensorRT CI Pipeline #7434: Pull request #25987 synchronize by quic-calvnguy
Action required CodeLinaro:quic_calvnguy/optrace_enablement
CodeLinaro:quic_calvnguy/optrace_enablement
Action required
[QNN-EP] Enable Optrace from QNN into QNN EP Windows GPU TensorRT CI Pipeline #7433: Pull request #25987 synchronize by quic-calvnguy
1h 58m 4s CodeLinaro:quic_calvnguy/optrace_enablement
CodeLinaro:quic_calvnguy/optrace_enablement
1h 58m 4s
Add partial data propagation to enhance shape inference Windows GPU TensorRT CI Pipeline #7432: Pull request #26269 synchronize by chilo-ms
2h 20m 27s chi/fix_shape_inference
chi/fix_shape_inference
2h 20m 27s
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7431: Pull request #26349 synchronize by tianleiwu
1h 57m 55s tlwu/cuda130
tlwu/cuda130
1h 57m 55s
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7430: Pull request #26349 synchronize by tianleiwu
3m 40s tlwu/cuda130
tlwu/cuda130
3m 40s
[CUDA] patch cutlass for C++20 Windows GPU TensorRT CI Pipeline #7429: Pull request #26369 opened by tianleiwu
2h 17m 44s tlwu/pacth_cutlass
tlwu/pacth_cutlass
2h 17m 44s
Address MLAS NchwcBlockSize for AMD64 platforms behavior in the minimal builds Windows GPU TensorRT CI Pipeline #7428: Pull request #26306 synchronize by yuslepukhin
2h 14m 35s yuslepukhin/fix_minimal_layout_transformation
yuslepukhin/fix_minimal_layout_transformation
2h 14m 35s
[Build] New docker image with GCC 14 and CUDA 12.8/13.0 Windows GPU TensorRT CI Pipeline #7427: Pull request #26349 synchronize by tianleiwu
1h 7m 3s tlwu/cuda130
tlwu/cuda130
1h 7m 3s
ORT 1.23.2 cherrypick 1 Windows GPU TensorRT CI Pipeline #7426: Pull request #26368 synchronize by apsonawane
2h 29m 26s asonawane/cherry-pick-1
asonawane/cherry-pick-1
2h 29m 26s
ORT 1.23.2 cherrypick 1 Windows GPU TensorRT CI Pipeline #7425: Pull request #26368 opened by apsonawane
20m 53s asonawane/cherry-pick-1
asonawane/cherry-pick-1
20m 53s
ORT 1.23.1 cherrypick 2 (#26182) Windows GPU TensorRT CI Pipeline #7424: Commit d9b2048 pushed by snnn
1h 52m 9s rel-1.23.2
rel-1.23.2
1h 52m 9s
Save much memory at model loading time by converting weights to OrtValues early Windows GPU TensorRT CI Pipeline #7423: Pull request #26345 synchronize by yuslepukhin
2h 14m 35s yuslepukhin/convert_weights_early
yuslepukhin/convert_weights_early
2h 14m 35s
Fix quantization in Whisper model export (#26353) Windows GPU TensorRT CI Pipeline #7422: Commit ed7847c pushed by kunal-vaishnavi
2h 13m 48s main
main
2h 13m 48s
[webgpu] Don't use num_workgroups when use indirect dispatch (#26334) Windows GPU TensorRT CI Pipeline #7421: Commit 8ab27d9 pushed by fs-eire
2h 31m 29s main
main
2h 31m 29s