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
Skip two SDPA fallback tests on ROCm, where AOTInductor cannot lower them pull #95564: Pull request #23383 synchronize by shoumikhin
Queued shoumikhin:rocm-skip-sdpa-regular-lowering
shoumikhin:rocm-skip-sdpa-regular-lowering
Queued
[LLM] Add Terminal-Bench evaluation scripts pull #95563: Pull request #23384 synchronize by mergennachin
In progress gh/mergennachin/39/head
gh/mergennachin/39/head
In progress
[LLM] Add Terminal-Bench evaluation scripts pull #95562: Pull request #23384 synchronize by mergennachin
3s gh/mergennachin/39/head
gh/mergennachin/39/head
3s
Ship the CUDA runtime in the Windows CUDA wheel pull #95561: Pull request #23123 synchronize by Gasoonjia
In progress gasoonjia/windows-cuda-sdk-wheel
gasoonjia/windows-cuda-sdk-wheel
In progress
Merge cuda-perf.yml into cuda.yml and add 5% perf regression gate (#23385) pull #95560: Pull request #23385 synchronize by meta-codesync Bot
In progress export-D123135327
export-D123135327
In progress
[RFC] Qualcomm AI Engine Direct - RFCs for Dataset calibration support and LoRA with LLMConfig pull #95559: Pull request #23386 opened by qti-mmadhava
Action required CodeLinaro:rfc_datasets_lora
CodeLinaro:rfc_datasets_lora
Action required
[LLM] Add Terminal-Bench evaluation scripts pull #95558: Pull request #23384 synchronize by mergennachin
17m 56s gh/mergennachin/39/head
gh/mergennachin/39/head
17m 56s
[LLM] Add Terminal-Bench evaluation scripts pull #95557: Pull request #23384 synchronize by mergennachin
3s gh/mergennachin/39/head
gh/mergennachin/39/head
3s
Merge cuda-perf.yml into cuda.yml and add 5% perf regression gate (#23385) pull #95556: Pull request #23385 opened by Gasoonjia
7m 57s export-D123135327
export-D123135327
7m 57s
[LLM] Add Terminal-Bench evaluation scripts pull #95555: Pull request #23384 synchronize by mergennachin
4m 14s gh/mergennachin/39/head
gh/mergennachin/39/head
4m 14s
[LLM] Add Terminal-Bench evaluation scripts pull #95554: Pull request #23384 synchronize by mergennachin
2s gh/mergennachin/39/head
gh/mergennachin/39/head
2s
[LLM] Add Terminal-Bench evaluation scripts pull #95553: Pull request #23384 synchronize by mergennachin
2s gh/mergennachin/39/head
gh/mergennachin/39/head
2s
[LLM] Add Terminal-Bench evaluation scripts pull #95552: Pull request #23384 synchronize by mergennachin
1m 58s gh/mergennachin/39/head
gh/mergennachin/39/head
1m 58s
[LLM] Add Terminal-Bench evaluation scripts pull #95551: Pull request #23384 opened by mergennachin
6m 37s gh/mergennachin/39/head
gh/mergennachin/39/head
6m 37s
Skip two SDPA fallback tests on ROCm, where AOTInductor cannot lower them pull #95550: Pull request #23383 opened by shoumikhin
46m 32s shoumikhin:rocm-skip-sdpa-regular-lowering
shoumikhin:rocm-skip-sdpa-regular-lowering
46m 32s
[LLM] Add Terminal-Bench evaluations and configurable CI pull #95549: Pull request #23382 opened by mergennachin
In progress llm/terminal-bench-evals
llm/terminal-bench-evals
In progress
Materialize zero bias for conv replacement (#23354) pull #95548: Commit 0b3d26d pushed by meta-codesync Bot
In progress main
main
In progress
[ET-VK][shaders] Harden UBO vector indexing for Adreno pull #95547: Pull request #23381 opened by SS-JIA
1h 38m 32s gh/SS-JIA/652/head
gh/SS-JIA/652/head
1h 38m 32s
Ship the CUDA runtime in the Windows CUDA wheel pull #95546: Pull request #23123 synchronize by Gasoonjia
1h 25m 17s gasoonjia/windows-cuda-sdk-wheel
gasoonjia/windows-cuda-sdk-wheel
1h 25m 17s
Stop publishing CUDA 13.0 wheels pull #95545: Pull request #23380 opened by shoumikhin
1h 45m 55s shoumikhin:stop-publishing-cuda-13-0-wheels
shoumikhin:stop-publishing-cuda-13-0-wheels
1h 45m 55s
Accept AOTI's compact clones of view buffers in the CUDA weight colle… pull #95544: Commit fbf91c2 pushed by shoumikhin
1h 48m 50s main
main
1h 48m 50s
Let the CUDA backend autotune matmuls on GPUs with fewer than 68 SMs … pull #95543: Commit 223455b pushed by shoumikhin
1h 34m 48s main
main
1h 34m 48s
Leave SDPA calls the Triton kernel cannot take to the regular CUDA lo… pull #95542: Commit 8a08ecd pushed by shoumikhin
1h 30m 25s main
main
1h 30m 25s
[cadence] Run one Cadence job tree for branch PRs and fork PRs pull #95541: Pull request #23379 opened by aliafzal
1h 24m 16s cadence-consolidate-ci
cadence-consolidate-ci
1h 24m 16s
Fix codegen pull #95540: Pull request #23378 opened by metascroy
1h 25m 40s metascroy:export-D123102340
metascroy:export-D123102340
1h 25m 40s