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
[MLAS] Add RISC-V RVV backend for MLAS QNBitGemm (MatMulNBits) Linux TensorRT CI #17247: Pull request #29537 synchronize by velonica0
Action required velonica0:qnbitgemm
velonica0:qnbitgemm
Action required
Add Intel WebGPU subgroup-matrix MatMul implementation Linux TensorRT CI #17246: Pull request #29592 synchronize by jchen10
1h 24m 34s jchen10:sgmm_up
jchen10:sgmm_up
1h 24m 34s
Fix usage of stream for memory pattern allocation with arena Linux TensorRT CI #17245: Pull request #29589 synchronize by skottmckay
1h 25m 7s skottmckay/FixArenaCleanupForRootStreamAllocation
skottmckay/FixArenaCleanupForRootStreamAllocation
1h 25m 7s
[WebGPU EP] Fix unnecessary CPU fallback and improve fallback diagnostic Linux TensorRT CI #17244: Pull request #29682 synchronize by mingmingtasd
Action required mingmingtasd:pr-webgpu-cpu-fallback-fix
mingmingtasd:pr-webgpu-cpu-fallback-fix
Action required
[Performance] Improve CPU masked attention performance Linux TensorRT CI #17243: Pull request #29719 opened by tianleiwu
1h 23m 37s tlwu/20260714/improve_cpu_att_mask_perf
tlwu/20260714/improve_cpu_att_mask_perf
1h 23m 37s
Fix GCC 15 -Werror build warnings Linux TensorRT CI #17242: Pull request #29679 synchronize by mirounga
Action required mirounga:rs_buf7
mirounga:rs_buf7
Action required
Enable cuDNN SDPA for contrib Attention Linux TensorRT CI #17241: Pull request #29717 synchronize by mastryukov1990
1h 36m 56s mastryukov1990:codex/attention-cudnn-padding-mask
mastryukov1990:codex/attention-cudnn-padding-mask
1h 36m 56s
Bump transformers from 4.52.1 to 5.5.0 in /tools/ci_build/requirements/transformers-test Linux TensorRT CI #17240: Pull request #29718 opened by dependabot Bot
1h 21m 56s dependabot/pip/tools/ci_build/requirements/transformers-test/transformers-5.5.0
dependabot/pip/tools/ci_build/requirements/transformers-test/transformers-5.5.0
1h 21m 56s
Add a cuDNN SDPA decode tier to the ONNX standard Attention CUDA kernel (Phase 1) Linux TensorRT CI #17239: Pull request #29715 synchronize by Copilot AI
1h 26m 46s copilot/add-cudnn-sdpa-decode-tier
copilot/add-cudnn-sdpa-decode-tier
1h 26m 46s
Enable cuDNN SDPA for contrib Attention Linux TensorRT CI #17238: Pull request #29717 opened by mastryukov1990
1h 28m 33s mastryukov1990:codex/attention-cudnn-padding-mask
mastryukov1990:codex/attention-cudnn-padding-mask
1h 28m 33s
Add a cuDNN SDPA decode tier to the ONNX standard Attention CUDA kernel (Phase 1) Linux TensorRT CI #17237: Pull request #29715 synchronize by Copilot AI
1h 1m 47s copilot/add-cudnn-sdpa-decode-tier
copilot/add-cudnn-sdpa-decode-tier
1h 1m 47s
Add a cuDNN SDPA decode tier to the ONNX standard Attention CUDA kernel (Phase 1) Linux TensorRT CI #17236: Pull request #29715 synchronize by Copilot AI
Action required copilot/add-cudnn-sdpa-decode-tier
copilot/add-cudnn-sdpa-decode-tier
Action required
[onnxruntime-web] Plans to deprecate and remove WebGL and JSEP Linux TensorRT CI #17235: Pull request #29716 opened by edgchen1
1h 29m 30s edgchen1/ort_web_backend_deprecation_plans
edgchen1/ort_web_backend_deprecation_plans
1h 29m 30s
Add a cuDNN SDPA decode tier to the ONNX standard Attention CUDA kernel (Phase 1) Linux TensorRT CI #17234: Pull request #29715 opened by Copilot AI
Action required copilot/add-cudnn-sdpa-decode-tier
copilot/add-cudnn-sdpa-decode-tier
Action required
[WebGPU] updates webgpu softmax to use online algorithm Linux TensorRT CI #17233: Pull request #29694 synchronize by prathikr
1h 20m 38s prathikrao/webgpu-online-softmax-impl-2
prathikrao/webgpu-online-softmax-impl-2
1h 20m 38s
Add POSIX telemetry Linux TensorRT CI #17232: Pull request #27379 synchronize by bmehta001
1h 32m 36s bhamehta/posix-telemetry
bhamehta/posix-telemetry
1h 32m 36s
Add POSIX telemetry Linux TensorRT CI #17231: Pull request #27379 synchronize by bmehta001
4s bhamehta/posix-telemetry
bhamehta/posix-telemetry
4s
[CUDA] Update cuda arch list for packages of cuda 12.8 Linux TensorRT CI #17230: Pull request #29711 opened by tianleiwu
1h 39m 56s tlwu/20260714/update_cuda_arch_list
tlwu/20260714/update_cuda_arch_list
1h 39m 56s
Add missing rank/length validation to pooling operators (fix OOB read… Linux TensorRT CI #17229: Commit a91b0b4 pushed by titaiwangms
1h 48m 16s main
main
1h 48m 16s
Add duplicate domain dedup check in AddCustomOpDomain Linux TensorRT CI #17228: Pull request #29661 synchronize by chilo-ms
1h 45m 9s chilo-ms/fix-customop-domain-dedup
chilo-ms/fix-customop-domain-dedup
1h 45m 9s
[CUDA] Fix XQA GroupQueryAttention cudaErrorInvalidValue on Blackwell (sm_120) Linux TensorRT CI #17227: Pull request #29706 synchronize by tianleiwu
1h 42m 10s tlwu/20260714/fix_xqa_sm120
tlwu/20260714/fix_xqa_sm120
1h 42m 10s
[web] Support Blob-backed external data for on-demand loading in JSPI… Linux TensorRT CI #17226: Commit 010a8f0 pushed by hariharans29
2h 15m 15s main
main
2h 15m 15s
[MLAS] Add AVX2 (+VNNI) 2-bit weight CPU kernels Linux TensorRT CI #17225: Pull request #29619 reopened by hariharans29
2h 4m 13s blazingphoenix7:mlas-avx2-w2
blazingphoenix7:mlas-avx2-w2
2h 4m 13s
[ORT] Extend reshape fusion Linux TensorRT CI #17224: Pull request #29027 reopened by hariharans29
1h 18m 50s Honry:webnn/reshape-fusion-dynamic
Honry:webnn/reshape-fusion-dynamic
1h 18m 50s
[MLAS] Integrate Q4 asymmetric KleidiAI kernels into MatMulNBits Linux TensorRT CI #17223: Pull request #29654 synchronize by martin-klacer-arm
1h 36m 13s martin-klacer-arm:markla01_integrate_4bit_asymmetric
martin-klacer-arm:markla01_integrate_4bit_asymmetric
1h 36m 13s