Skip to content

Actions: microsoft/onnxruntime

Actions

Linux TensorRT CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
linux_tensorrt_ci.yml
2,500+ workflow runs
2,500+ 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
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14948: Pull request #28501 synchronize by feich-ms
1h 38m 45s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
1h 38m 45s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14947: Pull request #28501 synchronize by feich-ms
34m 40s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
34m 40s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14946: Pull request #28501 synchronize by feich-ms
35m 28s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
35m 28s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14945: Pull request #28501 synchronize by feich-ms
9m 35s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
9m 35s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14944: Pull request #28501 synchronize by feich-ms
46s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
46s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14943: Pull request #28501 synchronize by feich-ms
10m 23s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
10m 23s
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14942: Pull request #28501 synchronize by feich-ms
18m 44s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
18m 44s
Add native Go binding for ONNX Runtime Linux TensorRT CI #14941: Pull request #28656 opened by mengzhuo
Action required mengzhuo:gobinding
mengzhuo:gobinding
Action required
[WebGPU] Support models with opset 24 ops and KV-shared decoder layers (Gemma 4) Linux TensorRT CI #14940: Pull request #28501 synchronize by feich-ms
30m 49s user/feich/webgpu-gemma4-opset24
user/feich/webgpu-gemma4-opset24
30m 49s
Update CUDA 12.8 to 13.0 in CI workflows Linux TensorRT CI #14939: Pull request #28458 synchronize by Copilot AI
1h 34m 12s copilot/update-ci-pipelines-to-cuda-13
copilot/update-ci-pipelines-to-cuda-13
1h 34m 12s
Fix CPU LSTM input validation and refactor ValidateInputs to frontends Linux TensorRT CI #14938: Pull request #28653 synchronize by vacu9708
Action required vacu9708:main
vacu9708:main
Action required
Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode Linux TensorRT CI #14937: Pull request #28645 synchronize by tianleiwu
1h 21m 58s tlwu/cuda_build_speedup
tlwu/cuda_build_speedup
1h 21m 58s
Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode Linux TensorRT CI #14936: Pull request #28645 synchronize by tianleiwu
38m 7s tlwu/cuda_build_speedup
tlwu/cuda_build_speedup
38m 7s
Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode Linux TensorRT CI #14935: Pull request #28645 synchronize by tianleiwu
28m 17s tlwu/cuda_build_speedup
tlwu/cuda_build_speedup
28m 17s
Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode Linux TensorRT CI #14934: Pull request #28645 synchronize by tianleiwu
1h 29m 20s tlwu/cuda_build_speedup
tlwu/cuda_build_speedup
1h 29m 20s
[MLAS] Optimize RISC-V RVV SGEMM kernel performance Linux TensorRT CI #14933: Pull request #28655 opened by zejianzhang1982
2h 34m 9s zte-riscv:rvv-sgemm-optimization
zte-riscv:rvv-sgemm-optimization
2h 34m 9s
js/node: offload Run() to thread pool via napi_async_work, add RunSync Linux TensorRT CI #14932: Pull request #28646 synchronize by A-KGeorge
Action required A-KGeorge:async-run-uv-queue-work
A-KGeorge:async-run-uv-queue-work
Action required
Speed up CUDA CI build: split into per-arch OBJECT libraries, add --flash_nvcc_threads, and enable quick build mode Linux TensorRT CI #14931: Pull request #28645 synchronize by tianleiwu
1h 22m 44s tlwu/cuda_build_speedup
tlwu/cuda_build_speedup
1h 22m 44s
Additional diagnostics for DML failure path (#28495) Linux TensorRT CI #14930: Commit a1fc916 pushed by adrastogi
1h 29m 52s main
main
1h 29m 52s
js/node: offload Run() to thread pool via napi_async_work, add RunSync Linux TensorRT CI #14929: Pull request #28646 synchronize by A-KGeorge
Action required A-KGeorge:async-run-uv-queue-work
A-KGeorge:async-run-uv-queue-work
Action required
Fix CPU LSTM input validation and refactor ValidateInputs to frontends Linux TensorRT CI #14928: Pull request #28653 synchronize by vacu9708
1h 36m 12s vacu9708:main
vacu9708:main
1h 36m 12s
Fix CPU LSTM input validation and refactor ValidateInputs to frontends Linux TensorRT CI #14927: Pull request #28653 opened by vacu9708
Action required vacu9708:main
vacu9708:main
Action required
fix 302 redirects while postinstall, with help of axios Linux TensorRT CI #14926: Pull request #28652 opened by phantom9999
Action required phantom9999:main
phantom9999:main
Action required
Propagate outer scope type info to subgraphs during verification Linux TensorRT CI #14925: Pull request #27707 synchronize by Rishi-Dave
1h 38m 13s Rishi-Dave:rishidave/fix/outer-scope-initializer-type-info
Rishi-Dave:rishidave/fix/outer-scope-initializer-type-info
1h 38m 13s
Fix: add missing fields to ToProviderOptions for CUDA Linux TensorRT CI #14924: Pull request #28651 opened by G3nna
1h 35m 56s G3nna:add_missing_fields_to_CUDAExecutionProviderInfo
G3nna:add_missing_fields_to_CUDAExecutionProviderInfo
1h 35m 56s