Skip to content

Actions: pytorch/executorch

Actions

cuda-perf

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
cuda-perf.yml
2,074 workflow runs
2,074 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
[ExecuTorch] Complete Muse Glimmer rename (#21863) cuda-perf #2077: Commit bd2e855 pushed by digantdesai
37s main
main
37s
Arm backend: Add to pre-push automatic list of supported ops - VGF (#… cuda-perf #2076: Commit 42ebbc3 pushed by wwwind
37s main
main
37s
Update Muse Glimmer GGUF filenames to canonical names (#21853) cuda-perf #2075: Commit ed65b12 pushed by sid-rp
1h 8m 47s main
main
1h 8m 47s
Update Muse Glimmer GGUF filenames to canonical names cuda-perf #2074: Pull request #21853 synchronize by sid-rp
1h 19m 13s muse-glimmer-gguf-names
muse-glimmer-gguf-names
1h 19m 13s
Update Muse Glimmer GGUF filenames to canonical names cuda-perf #2073: Pull request #21853 opened by sid-rp
1h 19m 42s muse-glimmer-gguf-names
muse-glimmer-gguf-names
1h 19m 42s
Fix QNN simulator failures after HadamardTransform support cuda-perf #2072: Commit 287ab8b pushed by meta-codesync Bot
1h 6m 23s main
main
1h 6m 23s
Write golden input artifacts in the tensor's own byte order (#21851) cuda-perf #2071: Commit d18ca0f pushed by rascani
44s main
main
44s
Updating QNN backend owners list (#21852) cuda-perf #2070: Commit d2ce778 pushed by psiddh
42s main
main
42s
Cortex-M: share one to_edge config instead of five hand-copied ones (… cuda-perf #2069: Commit e53b7a1 pushed by rascani
50s main
main
50s
Reseed the Cortex-M test RNG before each test module is imported (#21… cuda-perf #2068: Commit 3253a28 pushed by rascani
1h 22m 25s main
main
1h 22m 25s
Cortex-M backend: supply a zero bias for grouped convolutions (#21825) cuda-perf #2067: Commit 66967ef pushed by rascani
39s main
main
39s
[release/1.4] Fix CUDA shared library packaging (#21850) cuda-perf #2066: Commit e4d02f4 pushed by JacobSzwejbka
39s release/1.4
release/1.4
39s
Treat an empty LLM data path as absent (#21835) cuda-perf #2065: Commit 88f0c74 pushed by JakeStevens
35s main
main
35s
Cortex-M: annotate and preserve in-place activations (#21819) cuda-perf #2064: Commit 33f68d1 pushed by rascani
42s main
main
42s
Add Windows ARM64 build CI (#21817) cuda-perf #2063: Commit 5c3cb65 pushed by JacobSzwejbka
1h 14m 26s main
main
1h 14m 26s
Arduino: correct the link mode guidance and pin the board core in CI … cuda-perf #2062: Commit 856aacb pushed by psiddh
41s main
main
41s
Fix XNN PreLU use after free (#21480) (#21845) cuda-perf #2061: Commit d974571 pushed by JacobSzwejbka
1h 0m 51s release/1.4
release/1.4
1h 0m 51s
Skip torchtune on Python 3.14 in the examples requirements (#21832) cuda-perf #2060: Commit ea3641d pushed by shoumikhin
38s main
main
38s
Skip the Core ML wheel test on Python 3.14 (#21841) cuda-perf #2059: Commit 813145d pushed by shoumikhin
38s main
main
38s
Arm backend: Fix Cortex-M55 CPU cycle measurements (#21833) cuda-perf #2058: Commit 79e3eae pushed by mansnils
1h 7m 25s main
main
1h 7m 25s
Arm backend: Cleanup and enable tests in test_batch_norm.py (#21836) cuda-perf #2057: Commit 09ba075 pushed by tom-arm
38s main
main
38s
Support bf16 activations in ExecuTorch XNNPACK export (#21784) cuda-perf #2056: Commit abc5586 pushed by meta-codesync Bot
38s main
main
38s
Retire attention-mask custom operator cuda-perf #2055: Commit 7dd3335 pushed by meta-codesync Bot
41s main
main
41s
Recognise the repeat_interleave idiom in RemovePermutesAroundElementw… cuda-perf #2054: Commit 7791a5f pushed by meta-codesync Bot
1h 5m 9s main
main
1h 5m 9s
Resolve Operator fallback to method allocator if temp alloc fails (#2… cuda-perf #2053: Commit 47e536d pushed by meta-codesync Bot
38s main
main
38s