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
[CUDA] Use Triton TMA for long-context causal prefill pull #91660: Pull request #22414 opened by Gasoonjia
Queued codex/stack-tma-prefill
codex/stack-tma-prefill
Queued
Pass the Apple event tracer's C++ handle opaquely across the framework boundary pull #91659: Pull request #22396 synchronize by shoumikhin
Queued fix-apple-tracer-seam
fix-apple-tracer-seam
Queued
Enable use_sdpa_with_kv_cache in the qwen3_5 example config (#22390) pull #91658: Commit 5b829f9 pushed by JakeStevens
Queued main
main
Queued
Run the Qualcomm SDK setup on the paths that need it pull #91657: Pull request #22395 synchronize by shoumikhin
In progress qnn-setup-on-the-paths-that-need-it
qnn-setup-on-the-paths-that-need-it
In progress
pull pull #91656: by pytorch-bot Bot
In progress ciflow/trunk/22412
ciflow/trunk/22412
In progress
Arm backend: Add bounded U55 unfold_copy support pull #91655: Pull request #22412 synchronize by perheld
In progress perheld:change-1321555
perheld:change-1321555
In progress
Report whether XNNPACK packed weights fell back to heap pull #91654: Pull request #22413 opened by doggeral
In progress doggeral:export-D118206001
doggeral:export-D118206001
In progress
Android: allow building Vulkan/XNNPACK backends as separate shared libraries pull #91653: Pull request #21849 synchronize by msluszniak
Action required msluszniak:ms/android-shared-backend-libs
msluszniak:ms/android-shared-backend-libs
Action required
[CUDA] Add Triton Q4_K-to-FP8 prefill linear pull #91652: Pull request #22192 synchronize by Gasoonjia
In progress codex/stack-q4k-fp8-prefill
codex/stack-q4k-fp8-prefill
In progress
[CUDA] Use Triton TMA for long-context causal prefill pull #91651: Pull request #22193 synchronize by Gasoonjia
In progress codex/stack-tma-prefill
codex/stack-tma-prefill
In progress
Save the etrecord the lowered paths already generate pull #91650: Pull request #22303 synchronize by shoumikhin
In progress shoumikhin:llama-etrecord-lowered
shoumikhin:llama-etrecord-lowered
In progress
Report the MLX backend as unavailable on the iOS simulator pull #91649: Pull request #22336 synchronize by shoumikhin
In progress shoumikhin:mlx-simulator-unavailable
shoumikhin:mlx-simulator-unavailable
In progress
Report the MLX backend as unavailable on the iOS simulator pull #91648: Pull request #22336 synchronize by shoumikhin
In progress shoumikhin:mlx-simulator-unavailable
shoumikhin:mlx-simulator-unavailable
In progress
Fold non-matching end permutes instead of discarding the region (#22293) pull #91647: Commit 0c6ecea pushed by meta-codesync Bot
In progress main
main
In progress
Stop reading a backend config field that no longer exists (#22298) pull #91646: Commit 2cd8f26 pushed by shoumikhin
In progress main
main
In progress
Build the flatc host tools for macOS on an iOS build pull #91645: Pull request #22304 synchronize by shoumikhin
1h 28m 35s fix-ios-deployment-target
fix-ios-deployment-target
1h 28m 35s
Run CUDA delegates on the per-thread stream pull #91644: Pull request #22318 synchronize by shoumikhin
1h 30m 47s shoumikhin:fix/cuda-delegate-per-thread-stream
shoumikhin:fix/cuda-delegate-per-thread-stream
1h 30m 47s
Keep the CUDA memory pool warm between delegates pull #91643: Pull request #22312 synchronize by shoumikhin
1h 31m 10s shoumikhin:fix/cuda-mempool-release-threshold
shoumikhin:fix/cuda-mempool-release-threshold
1h 31m 10s
pull pull #91642: by pytorch-bot Bot
1h 37m 26s ciflow/trunk/20515
ciflow/trunk/20515
1h 37m 26s
XNNPACK: Lift constant mul scalars for partitioning pull #91641: Pull request #20515 synchronize by mansnils
1h 36m 39s mansnils:ops
mansnils:ops
1h 36m 39s
Run the Qualcomm SDK setup on the paths that need it pull #91640: Pull request #22395 synchronize by shoumikhin
1h 37m 26s qnn-setup-on-the-paths-that-need-it
qnn-setup-on-the-paths-that-need-it
1h 37m 26s
pull pull #91639: by pytorch-bot Bot
3m 44s ciflow/trunk/20515
ciflow/trunk/20515
3m 44s
XNNPACK: Lift constant mul scalars for partitioning pull #91638: Pull request #20515 synchronize by mansnils
1h 24m 0s mansnils:ops
mansnils:ops
1h 24m 0s
Run CUDA delegates on the per-thread stream pull #91637: Pull request #22318 synchronize by shoumikhin
1h 23m 33s shoumikhin:fix/cuda-delegate-per-thread-stream
shoumikhin:fix/cuda-delegate-per-thread-stream
1h 23m 33s
Keep the CUDA memory pool warm between delegates pull #91636: Pull request #22312 synchronize by shoumikhin
1h 24m 25s shoumikhin:fix/cuda-mempool-release-threshold
shoumikhin:fix/cuda-mempool-release-threshold
1h 24m 25s