Skip to content

Actions: pytorch/executorch

Actions

pull

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
pull.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
pull pull #72867: by pytorch-bot Bot
1h 25m 15s ciflow/trunk/18827
ciflow/trunk/18827
1h 25m 15s
Add FuseConcatPass to eliminate redundant concat ops (#18827) pull #72866: Pull request #18827 synchronize by ryan-monroe
2h 50m 6s ryan-monroe:export-D97667069
ryan-monroe:export-D97667069
2h 50m 6s
Place model PTE in DDR to fix FVP link-time memory overflow (#19199) pull #72865: Commit ddd8ac6 pushed by psiddh
3h 42m 52s main
main
3h 42m 52s
Qualcomm AI Engine Direct - Update CLI tool to dump inference performace pull #72864: Pull request #18085 synchronize by chenweng-quic
3h 44m 37s CodeLinaro:dev1/chenweng/cli_etdump
CodeLinaro:dev1/chenweng/cli_etdump
3h 44m 37s
[ETVK] WebGPU runtime (#18808) pull #72863: Commit 173c9e2 pushed by digantdesai
4h 4m 17s main
main
4h 4m 17s
pull pull #72862: by pytorch-bot Bot
1h 28m 38s ciflow/trunk/19206
ciflow/trunk/19206
1h 28m 38s
XNNPACK: accept positive spatial dims in mean.dim via normalization pull #72861: Pull request #19206 opened by mansnils
4h 17m 38s mansnils:xnnpack
mansnils:xnnpack
4h 17m 38s
NXP backend: Add use new flag to custom compilation options, add op aliases pull #72860: Pull request #19184 synchronize by roman-janik-nxp
3h 33m 12s nxp-upstream:feature/nxg11066/EIEX-898-Add-use-new-flag-to-custom-compilation-options,-add-op-aliases
nxp-upstream:feature/nxg11066/EIEX-898-Add-use-new-flag-to-custom-compilation-options,-add-op-aliases
3h 33m 12s
NXP backend: Test avg_pool2d with new Neutron flow. pull #72859: Pull request #19147 synchronize by MartinPavella
3h 49m 38s nxp-upstream:nxg01483/EIEX-858-add-avg_pool2d-support-using-new-neutron-flow
nxp-upstream:nxg01483/EIEX-858-add-avg_pool2d-support-using-new-neutron-flow
3h 49m 38s
Add Gemma 4 MLX install-path support pull #72858: Pull request #19065 synchronize by zeel2104
3h 30m 19s zeel2104:gemma4-mlx-install-path
zeel2104:gemma4-mlx-install-path
3h 30m 19s
NXP backend: Unify testing infrastructure. (#19112) pull #72857: Commit eb19f24 pushed by MartinPavella
2h 6m 58s main
main
2h 6m 58s
Qualcomm AI Engine Direct - Update CLI tool to dump inference performace pull #72856: Pull request #18085 synchronize by chenweng-quic
2h 12m 21s CodeLinaro:dev1/chenweng/cli_etdump
CodeLinaro:dev1/chenweng/cli_etdump
2h 12m 21s
NXP backend: Add QuantizeFusedConvBnBiasAtenPass call to integration tests pipeline pull #72855: Pull request #18904 synchronize by StrycekSimon
3h 40m 25s nxp-upstream:feature/nxg10272/EIEX-757-enable-mlperftiny-vww-model-qat-training-test
nxp-upstream:feature/nxg10272/EIEX-757-enable-mlperftiny-vww-model-qat-training-test
3h 40m 25s
NXP backend: Add QuantizeFusedConvBnBiasAtenPass call to integration tests pipeline pull #72854: Pull request #18904 synchronize by StrycekSimon
35m 9s nxp-upstream:feature/nxg10272/EIEX-757-enable-mlperftiny-vww-model-qat-training-test
nxp-upstream:feature/nxg10272/EIEX-757-enable-mlperftiny-vww-model-qat-training-test
35m 9s
Enable Qwen3.5-MoE AOTI export on memory-constrained GPUs pull #72853: Pull request #19205 opened by Gasoonjia
3h 41m 44s cuda-aoti-low-mem-export
cuda-aoti-low-mem-export
3h 41m 44s
Qualcomm AI Engine Direct - Fixed arange dtype pull #72852: Pull request #19204 opened by shewu-quic
3h 32m 52s CodeLinaro:dev1/hutton/fixed_arange_dtype
CodeLinaro:dev1/hutton/fixed_arange_dtype
3h 32m 52s
NXP backend: added support for aten.conv_transpose1 and refactored convolution_converter pull #72851: Pull request #19004 synchronize by novak-vaclav
2h 34m 4s nxp-upstream:feature/EIEX-681-add-transposed-conv-1d-support
nxp-upstream:feature/EIEX-681-add-transposed-conv-1d-support
2h 34m 4s
pull pull #72850: by pytorch-bot Bot
3h 41m 52s ciflow/trunk/19199
ciflow/trunk/19199
3h 41m 52s
Place model PTE in DDR to fix FVP link-time memory overflow pull #72849: Pull request #19199 synchronize by psiddh
3h 37m 21s psiddh:fix-mv2-fvp-memory-overflow
psiddh:fix-mv2-fvp-memory-overflow
3h 37m 21s
NXP backend: Test avg_pool2d with new Neutron flow. pull #72848: Pull request #19147 synchronize by MartinPavella
2h 1m 13s nxp-upstream:nxg01483/EIEX-858-add-avg_pool2d-support-using-new-neutron-flow
nxp-upstream:nxg01483/EIEX-858-add-avg_pool2d-support-using-new-neutron-flow
2h 1m 13s
pull pull #72847: by pytorch-bot Bot
3h 41m 30s ciflow/trunk/19199
ciflow/trunk/19199
3h 41m 30s
Place model PTE in DDR to fix FVP link-time memory overflow pull #72846: Pull request #19199 synchronize by psiddh
15m 2s psiddh:fix-mv2-fvp-memory-overflow
psiddh:fix-mv2-fvp-memory-overflow
15m 2s
Qualcomm AI Engine Direct - LPAI Direct Mode Support pull #72845: Pull request #19142 synchronize by winskuo-quic
3h 36m 29s CodeLinaro:dev1/winskuo/lpai_direct_mode
CodeLinaro:dev1/winskuo/lpai_direct_mode
3h 36m 29s
Qualcomm AI Engine Direct - LPAI Direct Mode Support pull #72844: Pull request #19142 synchronize by winskuo-quic
19m 31s CodeLinaro:dev1/winskuo/lpai_direct_mode
CodeLinaro:dev1/winskuo/lpai_direct_mode
19m 31s
Make the output of MoE forward method have expected output in non cuda backends pull #72843: Pull request #19170 synchronize by Gasoonjia
3h 30m 50s moe-no-float
moe-no-float
3h 30m 50s