Skip to content

Actions: microsoft/onnxruntime

Actions

Linux WebGPU CI

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
linux_webgpu.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] Optimize Qualcomm FP16 prefill attention Linux WebGPU CI #22691: Pull request #33724 synchronize by gyagp
36m 20s gyagp:pr/webgpu-qualcomm-prefill-attention
gyagp:pr/webgpu-qualcomm-prefill-attention
36m 20s
Build WebGPU plugin EP separately for Windows documentation generation Linux WebGPU CI #22690: Pull request #33829 synchronize by edgchen1
36m 16s edgchen1/fix_doc_gen_pipeline
edgchen1/fix_doc_gen_pipeline
36m 16s
Retain Node WebGPU output resources (#33741) Linux WebGPU CI #22689: Commit 34d4ec2 pushed by apsonawane
36m 11s main
main
36m 11s
Validate serialized prepacked buffers (#33499) Linux WebGPU CI #22688: Commit 6843e59 pushed by apsonawane
34m 34s main
main
34m 34s
Validate Whisper timestamp token bounds (#33824) Linux WebGPU CI #22687: Commit 585d6a6 pushed by apsonawane
32m 36s main
main
32m 36s
[CUDA] Optimize INT4 QMoE offload prefill/decode and S=8 doorbell exe… Linux WebGPU CI #22686: Commit 8e59de3 pushed by tianleiwu
32m 40s main
main
32m 40s
Support native file handles for external initializers Linux WebGPU CI #22685: Pull request #33660 synchronize by mustjab
32m 27s user/mustjab/upstream-linux-file-sources
user/mustjab/upstream-linux-file-sources
32m 27s
[WebGPU] Unroll bounded NVIDIA FlashAttention reductions in WGSL Linux WebGPU CI #22684: Pull request #33395 synchronize by gyagp
Action required gyagp:codex/webgpu-nvidia-flash-unroll-20261015
gyagp:codex/webgpu-nvidia-flash-unroll-20261015
Action required
[WebGPU] Unroll bounded NVIDIA FlashAttention reductions in WGSL Linux WebGPU CI #22683: Pull request #33395 synchronize by gyagp
Action required gyagp:codex/webgpu-nvidia-flash-unroll-20261015
gyagp:codex/webgpu-nvidia-flash-unroll-20261015
Action required
[WebGPU] Unroll bounded NVIDIA FlashAttention reductions in WGSL Linux WebGPU CI #22682: Pull request #33395 synchronize by gyagp
-1s gyagp:codex/webgpu-nvidia-flash-unroll-20261015
gyagp:codex/webgpu-nvidia-flash-unroll-20261015
-1s
Validate Resize linear index bounds (#33497) Linux WebGPU CI #22681: Commit 1e4bfba pushed by apsonawane
32m 13s main
main
32m 13s
[WebGPU] Unroll bounded NVIDIA FlashAttention reductions in WGSL Linux WebGPU CI #22680: Pull request #33395 synchronize by gyagp
Action required gyagp:codex/webgpu-nvidia-flash-unroll-20261015
gyagp:codex/webgpu-nvidia-flash-unroll-20261015
Action required
[WebGPU] Optimize Qualcomm FP16 prefill attention Linux WebGPU CI #22679: Pull request #33724 synchronize by gyagp
Action required gyagp:pr/webgpu-qualcomm-prefill-attention
gyagp:pr/webgpu-qualcomm-prefill-attention
Action required
[WebGPU] Optimize Qualcomm FP16 prefill attention Linux WebGPU CI #22678: Pull request #33724 synchronize by gyagp
Action required gyagp:pr/webgpu-qualcomm-prefill-attention
gyagp:pr/webgpu-qualcomm-prefill-attention
Action required
[CPU] Support right-padded prefill chunks in GroupQueryAttention Linux WebGPU CI #22677: Pull request #33505 synchronize by tianleiwu
32m 40s tlwu/gqa_cpu_right_padded_prefill_chunk_slide_window
tlwu/gqa_cpu_right_padded_prefill_chunk_slide_window
32m 40s
[CUDA] Support right-padded prefill chunks in GroupQueryAttention (#3… Linux WebGPU CI #22676: Commit 734eea3 pushed by tianleiwu
32m 32s main
main
32m 32s
Align WebGPU CPU/GPU profiling and add a Node.js trace viewer Linux WebGPU CI #22675: Pull request #33781 synchronize by gyagp
Action required gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
Action required
Align WebGPU CPU/GPU profiling and add a Node.js trace viewer Linux WebGPU CI #22674: Pull request #33781 synchronize by gyagp
Action required gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
Action required
Align WebGPU CPU/GPU profiling and add a Node.js trace viewer Linux WebGPU CI #22673: Pull request #33781 synchronize by gyagp
Action required gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
gyagp:pr-improve-profile-a82348b4-e08a-4244-9eb6-5ffa9998ddec
Action required
Add EP device memory capacity query API with CUDA support Linux WebGPU CI #22672: Pull request #33447 synchronize by selenayang888
1h 13m 44s syang/ep-device-memory-capacity
syang/ep-device-memory-capacity
1h 13m 44s
Build WebGPU plugin EP separately for Windows documentation generation Linux WebGPU CI #22671: Pull request #33829 synchronize by edgchen1
1h 11m 30s edgchen1/fix_doc_gen_pipeline
edgchen1/fix_doc_gen_pipeline
1h 11m 30s
Verify downloaded Node packages Linux WebGPU CI #22670: Pull request #33500 synchronize by apsonawane
1h 19m 19s fix/node-package-integrity
fix/node-package-integrity
1h 19m 19s
Validate MoE hidden dimensions Linux WebGPU CI #22669: Pull request #33820 synchronize by apsonawane
1h 17m 9s fix/moe-hidden-size-validation
fix/moe-hidden-size-validation
1h 17m 9s
Retain Node WebGPU output resources Linux WebGPU CI #22668: Pull request #33741 synchronize by apsonawane
1h 13m 33s fix/node-webgpu-lifetime
fix/node-webgpu-lifetime
1h 13m 33s
[CUDA] Optimize INT4 QMoE offload prefill/decode and S=8 doorbell execution Linux WebGPU CI #22667: Pull request #33622 synchronize by tianleiwu
1h 16m 18s tlwu/20261026/qmoe-offload-s8-int4-opt
tlwu/20261026/qmoe-offload-s8-int4-opt
1h 16m 18s