Skip to content

Actions: pytorch/executorch

Actions

Test XNNPACK Backend

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
test-backend-xnnpack.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
Bump @remix-run/node from 2.15.0 to 2.17.3 in /examples/demo-apps/react-native/rnllama Test XNNPACK Backend #3103: Pull request #16511 synchronize by psiddh
1h 2m 30s dependabot/npm_and_yarn/examples/demo-apps/react-native/rnllama/remix-run/node-2.17.3
dependabot/npm_and_yarn/examples/demo-apps/react-native/rnllama/remix-run/node-2.17.3
1h 2m 30s
Bump lodash from 4.17.23 to 4.18.1 in /examples/demo-apps/react-nativ… Test XNNPACK Backend #3102: Commit 3779b02 pushed by psiddh
1h 1m 11s main
main
1h 1m 11s
Fix integer overflows in tensor byte-size computations (#19055) Test XNNPACK Backend #3101: Commit 30f6b89 pushed by lucylq
1h 0m 24s main
main
1h 0m 24s
Add multi-reader tests for Add/Sub rescale fusion (#18758) Test XNNPACK Backend #3100: Pull request #18758 synchronize by meta-codesync Bot
1h 3m 39s export-D99939008
export-D99939008
1h 3m 39s
Qualcomm AI Engine Direct - Fixed Conv2d + PReLu fusion issue (#19014) Test XNNPACK Backend #3099: Commit 89587c2 pushed by abhinaykukkadapu
1h 0m 17s main
main
1h 0m 17s
Enable test_qnn_delegate tests to run on PR (#19050) Test XNNPACK Backend #3098: Pull request #19050 synchronize by abhinaykukkadapu
55m 32s abhinaykukkadapu:export-D102010420
abhinaykukkadapu:export-D102010420
55m 32s
Add multi-reader tests for Add/Sub rescale fusion (#18758) Test XNNPACK Backend #3097: Pull request #18758 synchronize by 3l1
7m 49s export-D99939008
export-D99939008
7m 49s
Add multi-reader tests for Add/Sub rescale fusion (#18758) Test XNNPACK Backend #3096: Pull request #18758 synchronize by meta-codesync Bot
4m 36s export-D99939008
export-D99939008
4m 36s
Fix overflows in et Test XNNPACK Backend #3095: Pull request #19057 opened by lucylq
1h 1m 19s security-17-overflows
security-17-overflows
1h 1m 19s
Enable test_qnn_delegate tests to run on PR (#19050) Test XNNPACK Backend #3094: Pull request #19050 synchronize by abhinaykukkadapu
1h 0m 50s abhinaykukkadapu:export-D102010420
abhinaykukkadapu:export-D102010420
1h 0m 50s
Per weight constant cache Test XNNPACK Backend #3093: Pull request #18901 synchronize by Gasoonjia
58m 43s per-weight-constant-cache
per-weight-constant-cache
58m 43s
Per weight constant cache Test XNNPACK Backend #3092: Pull request #18901 synchronize by Gasoonjia
6m 22s per-weight-constant-cache
per-weight-constant-cache
6m 22s
Unique .so paths to support multiple CUDA delegates Test XNNPACK Backend #3091: Pull request #19056 opened by skrtskrtfb
58m 56s skrtskrtfb:export-D101883539
skrtskrtfb:export-D101883539
58m 56s
Fix integer overflow in compute_numel() Test XNNPACK Backend #3090: Pull request #18598 synchronize by lucylq
1h 0m 53s security19
security19
1h 0m 53s
Fix integer overflows in tensor byte-size computations Test XNNPACK Backend #3089: Pull request #19055 opened by lucylq
1h 8m 26s security-19
security-19
1h 8m 26s
Bump lodash from 4.17.23 to 4.18.1 in /examples/demo-apps/react-native/rnllama Test XNNPACK Backend #3088: Pull request #18685 synchronize by psiddh
1h 1m 1s dependabot/npm_and_yarn/examples/demo-apps/react-native/rnllama/lodash-4.18.1
dependabot/npm_and_yarn/examples/demo-apps/react-native/rnllama/lodash-4.18.1
1h 1m 1s
Qualcomm AI Engine Direct - Adding QNN backend support for atan2 core ATen ops Test XNNPACK Backend #3087: Pull request #19051 synchronize by qti-horodnic
56m 23s CodeLinaro:atan2
CodeLinaro:atan2
56m 23s
Add multi-reader tests for Add/Sub rescale fusion (#18758) Test XNNPACK Backend #3086: Pull request #18758 synchronize by meta-codesync Bot
1h 0m 39s export-D99939008
export-D99939008
1h 0m 39s
Fix integer overflow in compute_numel() Test XNNPACK Backend #3085: Pull request #18598 synchronize by lucylq
57m 22s security19
security19
57m 22s
Fix integer overflow in compute_numel() Test XNNPACK Backend #3084: Pull request #18598 synchronize by lucylq
4m 45s security19
security19
4m 45s
MLX delegate: add integer support for aten.bitwise_not Test XNNPACK Backend #3083: Pull request #19053 opened by AlessandroVacca
14m 45s AlessandroVacca:mlx-bitwise-not-int
AlessandroVacca:mlx-bitwise-not-int
14m 45s
[QNN] Fix LiftConstantScalarOperands to handle aten.pow.Scalar (#18994) Test XNNPACK Backend #3082: Commit 0919746 pushed by abhinaykukkadapu
1h 8m 47s main
main
1h 8m 47s
Metal CI: Add Qwen 3.5 MoE tiny model integration test (#19042) Test XNNPACK Backend #3081: Commit 84e1aed pushed by manuelcandales
1h 6m 18s main
main
1h 6m 18s
Enable test_qnn_delegate tests to run on PR (#19050) Test XNNPACK Backend #3080: Pull request #19050 synchronize by abhinaykukkadapu
59m 7s abhinaykukkadapu:export-D102010420
abhinaykukkadapu:export-D102010420
59m 7s
Add Qwen 3.5 MoE to cuda-perf CI and add prefill throughput tracking Test XNNPACK Backend #3079: Pull request #18903 synchronize by Gasoonjia
58m 31s cuda-perf-qwen35-moe
cuda-perf-qwen35-moe
58m 31s
ProTip! You can narrow down the results and go further in time using created:<2026-04-22 or the other filters available.