Skip to content

Actions: pytorch/executorch

Actions

Test WebGPU Backend

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
test-backend-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
Arm backend: Handle empty target-less model suite (#21453) Test WebGPU Backend #5405: Commit 4a740f5 pushed by Sebastian-Larsson
In progress main
main
In progress
Arm backend: Remove Qwen3-VL BF16 patch embedding xfail (#21421) Test WebGPU Backend #5403: Commit e3eab48 pushed by Sebastian-Larsson
In progress main
main
In progress
Arm backend: Add MobileSAM Ethos-U example Test WebGPU Backend #5402: Pull request #21397 synchronize by usamahz
In progress usamahz:codex/mobilesam-ethosu-example-github
usamahz:codex/mobilesam-ethosu-example-github
In progress
[executorch][cuda] Optimize short-query INT5 matvec kernels Test WebGPU Backend #5401: Pull request #21458 opened by Gasoonjia
In progress gh/gasoonjia/177/head
gh/gasoonjia/177/head
In progress
[executorch][cuda] Optimize short-query INT6 matvec kernels Test WebGPU Backend #5400: Pull request #21457 opened by Gasoonjia
In progress gh/gasoonjia/176/head
gh/gasoonjia/176/head
In progress
[executorch][cuda] Optimize short-query INT4 matvec kernels Test WebGPU Backend #5399: Pull request #21456 opened by Gasoonjia
In progress gh/gasoonjia/175/head
gh/gasoonjia/175/head
In progress
Arm backend: Remove stale pre-commit hook setup Test WebGPU Backend #5398: Pull request #21419 synchronize by FabulousSuperDude
In progress FabulousSuperDude:fix_arm_setup_script
FabulousSuperDude:fix_arm_setup_script
In progress
Update eIQ Neutron SDK to 3.2.0 Test WebGPU Backend #5397: Pull request #21438 synchronize by irtrukhina
1h 3m 20s nxp-upstream:feature/neutron-software-3.2.0-updates
nxp-upstream:feature/neutron-software-3.2.0-updates
1h 3m 20s
Arm backend: add VGF runtime accuracy comparisons Test WebGPU Backend #5396: Pull request #21396 synchronize by robell
1h 0m 33s gh/robell/02-rife-runtime-accuracy
gh/robell/02-rife-runtime-accuracy
1h 0m 33s
Qualcomm AI Engine Direct - Gemma4 Text model enablement Test WebGPU Backend #5395: Pull request #20979 synchronize by DannyYuyang-quic
Action required CodeLinaro:dev1/danny/gemma4
CodeLinaro:dev1/danny/gemma4
Action required
Use dynamic CPU count for -j in vendor/example scripts and docs Test WebGPU Backend #5394: Pull request #21455 opened by ShamSaleem
Action required ShamSaleem:fix/10887-portable-cmake-jobs-followup
ShamSaleem:fix/10887-portable-cmake-jobs-followup
Action required
Arm backend: run RIFE QAT flow in channels-last (#21395) Test WebGPU Backend #5393: Commit 1f7c6d0 pushed by robell
1h 4m 56s main
main
1h 4m 56s
Arm backend: Add more tests to VGF Test WebGPU Backend #5392: Pull request #21454 opened by wwwind
1h 3m 43s wwwind:vgf_tests2
wwwind:vgf_tests2
1h 3m 43s
Arm backend: Handle empty target-less model suite Test WebGPU Backend #5391: Pull request #21453 opened by Sebastian-Larsson
1h 2m 26s Sebastian-Larsson:targetless_suite
Sebastian-Larsson:targetless_suite
1h 2m 26s
Update eIQ Neutron SDK to 3.2.0 Test WebGPU Backend #5390: Pull request #21438 synchronize by irtrukhina
1h 7m 0s nxp-upstream:feature/neutron-software-3.2.0-updates
nxp-upstream:feature/neutron-software-3.2.0-updates
1h 7m 0s
[ExecuTorch][llm] Add numerical kernel tests for quantized_moe_ffn Test WebGPU Backend #5389: Pull request #21123 synchronize by digantdesai
1h 3m 25s gh/digantdesai/73/head
gh/digantdesai/73/head
1h 3m 25s
[ExecuTorch][llm] Add MoE source transformation with INT4 quantized packing Test WebGPU Backend #5388: Pull request #21121 synchronize by digantdesai
1h 4m 25s gh/digantdesai/71/head
gh/digantdesai/71/head
1h 4m 25s
[ExecuTorch][llm] Wire --use_moe_quantized_op through export pipeline and LLM config Test WebGPU Backend #5387: Pull request #21126 synchronize by digantdesai
1h 4m 51s gh/digantdesai/76/head
gh/digantdesai/76/head
1h 4m 51s
[ExecuTorch][llm] Add Meta kernel and registration probe for quantized_moe_ffn Test WebGPU Backend #5386: Pull request #21120 synchronize by digantdesai
1h 3m 29s gh/digantdesai/70/head
gh/digantdesai/70/head
1h 3m 29s
[ExecuTorch][llm] Add quantized_moe_ffn custom op with C++ kernel Test WebGPU Backend #5385: Pull request #21119 synchronize by digantdesai
1h 2m 17s gh/digantdesai/69/head
gh/digantdesai/69/head
1h 2m 17s
[ExecuTorch][llm] Add source-transform and Meta-kernel tests for MoE op Test WebGPU Backend #5384: Pull request #21122 synchronize by digantdesai
1h 2m 45s gh/digantdesai/72/head
gh/digantdesai/72/head
1h 2m 45s
[ExecuTorch][llm] Fuse w1+w3 into single GEMM in quantized_moe_ffn Test WebGPU Backend #5383: Pull request #21124 synchronize by digantdesai
1h 3m 9s gh/digantdesai/74/head
gh/digantdesai/74/head
1h 3m 9s
[ExecuTorch][llm] Add MoE quantized custom op documentation Test WebGPU Backend #5382: Pull request #21125 synchronize by digantdesai
1h 3m 21s gh/digantdesai/75/head
gh/digantdesai/75/head
1h 3m 21s
Qualcomm AI Engine Direct - Pytest Refactor for Passes Test WebGPU Backend #5381: Pull request #21003 synchronize by winskuo-quic
1h 26m 33s CodeLinaro:dev1/winskuo/test_framework_refactor_passes
CodeLinaro:dev1/winskuo/test_framework_refactor_passes
1h 26m 33s
Qualcomm AI Engine Direct - Adding QNN backend support for the sort c… Test WebGPU Backend #5380: Commit d0fe35d pushed by psiddh
1h 3m 24s main
main
1h 3m 24s