Skip to content

Actions: pytorch/executorch

Actions

Test ARM Backend

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
test-backend-arm.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 pass to replace some ops with channels last variants. Test ARM Backend #10989: Pull request #20788 synchronize by MartinPavella
33m 1s nxp-upstream:nxg01483/EIEX-992-create-tocontiguouschannelslastpass
nxp-upstream:nxg01483/EIEX-992-create-tocontiguouschannelslastpass
33m 1s
Fuse consecutive clamps into a single clamp (#21013) Test ARM Backend #10988: Pull request #21013 opened by apullin
33m 19s apullin:export-D112351522
apullin:export-D112351522
33m 19s
Allow context-binary lowering to use edge dialect ops (#20518) Test ARM Backend #10987: Pull request #20518 synchronize by JakeStevens
40m 19s JakeStevens:export-D109598309
JakeStevens:export-D109598309
40m 19s
Allow context-binary lowering to use edge dialect ops (#20518) Test ARM Backend #10986: Pull request #20518 synchronize by JakeStevens
3m 17s JakeStevens:export-D109598309
JakeStevens:export-D109598309
3m 17s
Arm backend: Dequantize quantized grid sample coordinates Test ARM Backend #10985: Pull request #20962 synchronize by robell
20m 2s gh/robell/arm-grid-stack/03-dequant
gh/robell/arm-grid-stack/03-dequant
20m 2s
Arm backend: Add DeepSeek-R1-Distill-Qwen FP8 layer tests Test ARM Backend #10984: Pull request #21012 opened by bdemirb
18m 14s bdemirb:baris_mletorch-2337_fp8_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
bdemirb:baris_mletorch-2337_fp8_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
18m 14s
NXP backend: added support for scalar args of elementary ops Test ARM Backend #10983: Pull request #21011 opened by novak-vaclav
18m 53s nxp-upstream:feature/EIEX-987-verify-and-fix-use-of-scalar-args
nxp-upstream:feature/EIEX-987-verify-and-fix-use-of-scalar-args
18m 53s
Arm backend: Add DeepSeek-R1-Distill-Qwen layer tests Test ARM Backend #10982: Pull request #21010 synchronize by bdemirb
22m 11s bdemirb:baris_mletorch-1918_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
bdemirb:baris_mletorch-1918_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
22m 11s
Arm backend: Add DeepSeek-R1-Distill-Qwen layer tests Test ARM Backend #10981: Pull request #21010 opened by bdemirb
7m 1s bdemirb:baris_mletorch-1918_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
bdemirb:baris_mletorch-1918_layer_test_DeepSeek_R1_Distill_Qwen_1.5B
7m 1s
Arm backend: Keep internal shared qspec with uint8 IO Test ARM Backend #10980: Pull request #20978 synchronize by bdemirb
22m 22s bdemirb:baris/1286838-keep-internal-shared-qspec-uint8
bdemirb:baris/1286838-keep-internal-shared-qspec-uint8
22m 22s
Arm backend: Avoid shared qspec bridges for uint8 IO (#20976) Test ARM Backend #10979: Commit 47fd0d8 pushed by bdemirb
1h 4m 3s main
main
1h 4m 3s
NPX backend: added support for aten.rsqrt using new Neutron MLIR flow Test ARM Backend #10978: Pull request #21009 opened by novak-vaclav
21m 43s nxp-upstream:feature/EIEX-891-add-support-for-rsqrt
nxp-upstream:feature/EIEX-891-add-support-for-rsqrt
21m 43s
Arm backend: Keep internal shared qspec with uint8 IO Test ARM Backend #10977: Pull request #20978 synchronize by bdemirb
22m 49s bdemirb:baris/1286838-keep-internal-shared-qspec-uint8
bdemirb:baris/1286838-keep-internal-shared-qspec-uint8
22m 49s
Arm backend: Avoid shared qspec bridges for uint8 IO Test ARM Backend #10976: Pull request #20976 synchronize by bdemirb
18m 11s bdemirb:baris/1286639-avoid-shared-qspec-uint8
bdemirb:baris/1286639-avoid-shared-qspec-uint8
18m 11s
NXP backend: added support for same/valid padding for conv2d (#… Test ARM Backend #10975: Commit f6cef83 pushed by novak-vaclav
55m 14s main
main
55m 14s
Arm backend: Add RIFE PTQ/QAT accuracy flow (#20974) Test ARM Backend #10974: Commit de5f619 pushed by robell
1h 5m 47s main
main
1h 5m 47s
[ExecuTorch][WebGPU] Make shader workgroup sizes runtime-configurable Test ARM Backend #10973: Pull request #21006 synchronize by JCNTH
51m 48s gh/JCNTH/86/orig
gh/JCNTH/86/orig
51m 48s
[ExecuTorch][WebGPU] Make shader workgroup sizes runtime-configurable Test ARM Backend #10972: Pull request #21006 synchronize by JCNTH
46s gh/JCNTH/86/orig
gh/JCNTH/86/orig
46s
[ExecuTorch][WebGPU] Remove the orphan q4gsw_linear_coop4 shader Test ARM Backend #10971: Pull request #21007 synchronize by JCNTH
52m 7s gh/JCNTH/87/orig
gh/JCNTH/87/orig
52m 7s
[ExecuTorch][WebGPU] Test: rms_norm workgroup size is runtime-configurable Test ARM Backend #10970: Pull request #21008 opened by pytorchbot
1h 4m 54s gh/JCNTH/88/orig
gh/JCNTH/88/orig
1h 4m 54s
[ExecuTorch][WebGPU] Remove the orphan q4gsw_linear_coop4 shader Test ARM Backend #10969: Pull request #21007 opened by pytorchbot
14m 21s gh/JCNTH/87/orig
gh/JCNTH/87/orig
14m 21s
[ExecuTorch][WebGPU] Make shader workgroup sizes runtime-configurable Test ARM Backend #10968: Pull request #21006 opened by pytorchbot
15m 39s gh/JCNTH/86/orig
gh/JCNTH/86/orig
15m 39s
[ExecuTorch][Vulkan] Add et_vk.adamw_step kernel (on-GPU AdamW optimizer step) Test ARM Backend #10967: Pull request #20937 synchronize by JCNTH
1h 4m 38s gh/JCNTH/76/head
gh/JCNTH/76/head
1h 4m 38s
[ExecuTorch][WebGPU] Tests for the adamw WebGPU ops Test ARM Backend #10966: Pull request #20936 synchronize by JCNTH
1h 4m 27s gh/JCNTH/75/head
gh/JCNTH/75/head
1h 4m 27s
[ExecuTorch][WebGPU] Add q4gsw training kernels (backward, weight-grad, requant) to the WebGPU backend Test ARM Backend #10965: Pull request #20931 synchronize by JCNTH
1h 4m 45s gh/JCNTH/70/head
gh/JCNTH/70/head
1h 4m 45s