Skip to content

Actions: pytorch/executorch

Actions

Test CUDA Builds

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
cuda.yml
1,673 workflow runs
1,673 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Export LLMs with Optimum docs (#15062) Test CUDA Builds #1412: Commit 9152f0a pushed by jackzhxng
55m 42s main
main
55m 42s
[pytorch hash update] update the pinned pytorch hash Test CUDA Builds #1411: Pull request #10955 synchronize by pytorchupdatebot
1h 1m 32s update-pytorch-commit-hash/15080763801-537-1
update-pytorch-commit-hash/15080763801-537-1
1h 1m 32s
Cadence ops: Add in singleton tensor default variants Test CUDA Builds #1410: Pull request #15199 synchronize by DrJessop
25m 1s DrJessop:export-D84842582
DrJessop:export-D84842582
25m 1s
Modify Hexagon SDK paths Test CUDA Builds #1409: Pull request #15291 opened by cccclai
1h 3m 30s cccclai-patch-5
cccclai-patch-5
1h 3m 30s
Add support for Vulkan lowering Test CUDA Builds #1408: Pull request #15290 opened by pssrawat
22m 23s pssrawat:export-D85087953
pssrawat:export-D85087953
22m 23s
fix: alert users that darwin is not supported Test CUDA Builds #1407: Pull request #15289 opened by Mistobaan
27m 8s Mistobaan:features/darwin-build
Mistobaan:features/darwin-build
27m 8s
make aoti_torch_empty_strided support creating incontiguous tensor Test CUDA Builds #1406: Pull request #15228 synchronize by Gasoonjia
1h 36m 41s gh/gasoonjia/59/head
gh/gasoonjia/59/head
1h 36m 41s
add module level benchmark for gemma3 model Test CUDA Builds #1405: Pull request #15241 synchronize by Gasoonjia
56m 51s gh/gasoonjia/60/head
gh/gasoonjia/60/head
56m 51s
make aoti_torch_empty_strided support creating incontiguous tensor Test CUDA Builds #1404: Pull request #15228 synchronize by Gasoonjia
56m 21s gh/gasoonjia/59/head
gh/gasoonjia/59/head
56m 21s
gemma3 e2e runner on cuda Test CUDA Builds #1403: Pull request #15282 synchronize by Gasoonjia
56m 53s gh/gasoonjia/61/head
gh/gasoonjia/61/head
56m 53s
Android Docs: Fix stale backend link (android-samsung-exynos) (#15287) Test CUDA Builds #1402: Commit d2aa141 pushed by psiddh
57m 28s main
main
57m 28s
Fix text_llm_runner kv cache pos count and use it for generate() Test CUDA Builds #1401: Pull request #15286 synchronize by kirklandsign
1h 28m 31s text-llm-pos
text-llm-pos
1h 28m 31s
Android Docs: Fix stale backend link (android-samsung-exynos) Test CUDA Builds #1400: Pull request #15287 synchronize by psiddh
32m 48s psiddh:android_doc_patch
psiddh:android_doc_patch
32m 48s
Android Docs: Fix stale backend link (android-samsung-exynos) Test CUDA Builds #1399: Pull request #15287 synchronize by psiddh
13m 47s psiddh:android_doc_patch
psiddh:android_doc_patch
13m 47s
Android Docs: Fix stale backend link (android-samsung-exynos) Test CUDA Builds #1398: Pull request #15287 opened by psiddh
23m 12s psiddh:android_doc_patch
psiddh:android_doc_patch
23m 12s
Fix text_llm_runner kv cache pos count and use it for generate() Test CUDA Builds #1397: Pull request #15286 opened by kirklandsign
57m 56s text-llm-pos
text-llm-pos
57m 56s
[doc] Update quantization instructions for clarity (#15284) Test CUDA Builds #1396: Commit 58bd91c pushed by mergennachin
1h 3m 51s main
main
1h 3m 51s
Fix the llm module e2e test (#15275) Test CUDA Builds #1395: Commit fe3c1dc pushed by phaiting
55m 37s main
main
55m 37s
Cadence ops: Support quantized_w8a32_linear Test CUDA Builds #1394: Commit 9b744b4 pushed by meta-codesync bot
55m 54s main
main
55m 54s
Minor perf improvements to quantized mat mul shader. Test CUDA Builds #1393: Pull request #15261 synchronize by trivedivivek
47m 35s trivedivivek:export-D84998542
trivedivivek:export-D84998542
47m 35s
Minor perf improvements to quantized mat mul shader. Test CUDA Builds #1392: Pull request #15261 synchronize by trivedivivek
22m 17s trivedivivek:export-D84998542
trivedivivek:export-D84998542
22m 17s
Improving quantized matmul performance by devectorizing shader. Test CUDA Builds #1391: Pull request #15274 synchronize by trivedivivek
22m 21s trivedivivek:export-D85023829
trivedivivek:export-D85023829
22m 21s
[doc] Update quantization instructions for clarity Test CUDA Builds #1390: Pull request #15284 opened by mergennachin
55m 30s mergennachin-patch-6
mergennachin-patch-6
55m 30s
gemma3 e2e runner on cuda Test CUDA Builds #1389: Pull request #15282 synchronize by Gasoonjia
1h 33m 31s gh/gasoonjia/61/head
gh/gasoonjia/61/head
1h 33m 31s
make aoti_torch_empty_strided support creating incontiguous tensor Test CUDA Builds #1388: Pull request #15228 synchronize by Gasoonjia
58m 1s gh/gasoonjia/59/head
gh/gasoonjia/59/head
58m 1s
ProTip! You can narrow down the results and go further in time using created:<2025-10-20 or the other filters available.