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
Add PR-blocking CI for QNN model tests, operator/model testsuite, and pass unit tests (#18854) Test XNNPACK Backend #2622: Pull request #18854 synchronize by abhinaykukkadapu
21s abhinaykukkadapu:export-D100708421
abhinaykukkadapu:export-D100708421
21s
Add OSS Buck build support and CI for Qualcomm backend (#18666) Test XNNPACK Backend #2621: Pull request #18666 synchronize by abhinaykukkadapu
1h 4m 44s abhinaykukkadapu:export-D99222617
abhinaykukkadapu:export-D99222617
1h 4m 44s
Add MLX op handler for aten.isnan Test XNNPACK Backend #2620: Pull request #18952 synchronize by metascroy
1h 6m 42s Jah-yee:add-mlx-op-handler-aten-isnan
Jah-yee:add-mlx-op-handler-aten-isnan
1h 6m 42s
Add MLX op handler for aten.isinf Test XNNPACK Backend #2619: Pull request #18936 synchronize by metascroy
58m 0s Ai-chan-0411:fix/mlx-isinf-handler
Ai-chan-0411:fix/mlx-isinf-handler
58m 0s
Use caching allocator for runner (#15730) Test XNNPACK Backend #2618: Pull request #15730 synchronize by kimishpatel
59m 44s gh/kimishpatel/213/head
gh/kimishpatel/213/head
59m 44s
Use caching allocator for runner (#15730) Test XNNPACK Backend #2617: Pull request #15730 synchronize by kimishpatel
6m 53s gh/kimishpatel/213/head
gh/kimishpatel/213/head
6m 53s
Minor speedup for model lowering: Skip redundant run_decompositions when no ops match decomp table (#18496) Test XNNPACK Backend #2616: Pull request #18496 synchronize by apullin
1h 1m 49s apullin:export-D96489903
apullin:export-D96489903
1h 1m 49s
[ExecuTorch][Llama][ez] Remove unwrap_tensor_subclass from 4w quantiz… Test XNNPACK Backend #2615: Commit 9576316 pushed by SS-JIA
1h 1m 50s main
main
1h 1m 50s
[ExecuTorch][Llama][ez] Remove unwrap_tensor_subclass from 4w quantization path Test XNNPACK Backend #2614: Pull request #18975 opened by pytorchbot
56m 48s gh/SS-JIA/521/orig
gh/SS-JIA/521/orig
56m 48s
Fix ConvertMmToBmmPass for quantized (int8/int16) mm ops Test XNNPACK Backend #2613: Pull request #18974 opened by apullin
1h 5m 38s apullin:export-D99857137
apullin:export-D99857137
1h 5m 38s
Arm backend: Fix int8 TABLE domain for sigmoid LUTs Test XNNPACK Backend #2612: Pull request #18973 opened by xingguo01
1h 2m 5s xingguo01:arm-backend-fix-luts-softmax
xingguo01:arm-backend-fix-luts-softmax
1h 2m 5s
Arm backend: Add TOSA AVG_POOL2D op (#18972) Test XNNPACK Backend #2611: Commit 1154d34 pushed by AdrianLundell
1h 2m 47s main
main
1h 2m 47s
Arm backend: Add MAX_POOL2D tosa dialect op (#18970) Test XNNPACK Backend #2610: Commit 04955b2 pushed by AdrianLundell
56m 30s main
main
56m 30s
Arm backend: allow global register for ArmBackend pass insertions (#1… Test XNNPACK Backend #2609: Commit 70fd62b pushed by robell
1h 2m 42s main
main
1h 2m 42s
Arm backend: Add TOSA AVG_POOL2D op Test XNNPACK Backend #2608: Pull request #18972 opened by SaoirseARM
1h 4m 54s SaoirseARM:toupstream/avg_pool
SaoirseARM:toupstream/avg_pool
1h 4m 54s
Arm backend: Add MAX_POOL2D tosa dialect op Test XNNPACK Backend #2607: Pull request #18970 opened by AdrianLundell
59m 25s AdrianLundell:change-1241099
AdrianLundell:change-1241099
59m 25s
Arm backend: Fix dynamic conv-padding condition (#18941) Test XNNPACK Backend #2606: Commit cb30495 pushed by oscarandersson8218
58m 59s main
main
58m 59s
Qualcomm AI Engine Direct - PTQ Mix precision guidance for LLMs Test XNNPACK Backend #2605: Pull request #18969 opened by DannyYuyang-quic
1h 0m 33s CodeLinaro:dev1/danny/mix_precision
CodeLinaro:dev1/danny/mix_precision
1h 0m 33s
Add MLX op handler for aten.bitwise_xor Test XNNPACK Backend #2604: Pull request #18931 synchronize by nanookclaw
Action required nanookclaw:mlx-bitwise-xor
nanookclaw:mlx-bitwise-xor
Action required
Update docs of moved aot_arm_compiler.py (#18943) Test XNNPACK Backend #2603: Commit 9d72936 pushed by martinlsm
1h 0m 45s main
main
1h 0m 45s
Arm backend: Split MLSDK setup flows and handle shaderFloat64 workaround Test XNNPACK Backend #2602: Commit 89255ab pushed by perheld
57m 33s main
main
57m 33s
Integrate attention sink into ET LLM export and runner (#18860) Test XNNPACK Backend #2601: Commit bb07e8b pushed by meta-codesync bot
56m 40s main
main
56m 40s
Add CUDA graph capture/replay for qwen 3.5 moe decode method Test XNNPACK Backend #2600: Pull request #18809 synchronize by Gasoonjia
1h 2m 53s cuda-graph
cuda-graph
1h 2m 53s
Arm backend: Fix dynamic conv-padding condition Test XNNPACK Backend #2599: Pull request #18941 synchronize by oscarandersson8218
59m 57s oscarandersson8218:conv_dynamic_pad_fix
oscarandersson8218:conv_dynamic_pad_fix
59m 57s
[ET Device Support] Parse device info from serialized tensor in tenso… Test XNNPACK Backend #2598: Commit e8487f3 pushed by Gasoonjia
59m 27s main
main
59m 27s