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
Insert write-back copy_ nodes at the earliest safe point pull #97023: Pull request #20744 synchronize by JPL11
Action required JPL11:early-write-back-copies
JPL11:early-write-back-copies
Action required
[ET-VK][test] Run operator benchmarks from one etvk_bench binary pull #97022: Commit 14bd3e6 pushed by SS-JIA
In progress main
main
In progress
[ET-VK][test] Run operator benchmarks from one etvk_bench binary pull #97021: Pull request #23725 opened by pytorchbot
In progress gh/SS-JIA/667/orig
gh/SS-JIA/667/orig
In progress
[ET-VK][test] Move operator benchmark binaries under ops/benchmark pull #97020: Pull request #23724 opened by pytorchbot
In progress gh/SS-JIA/666/orig
gh/SS-JIA/666/orig
In progress
[ET-VK][gemm] Nest linear and matmul sources by scheme pull #97019: Pull request #23723 opened by pytorchbot
In progress gh/SS-JIA/660/orig
gh/SS-JIA/660/orig
In progress
[ET-VK][convolution] Nest convolution sources by route pull #97018: Pull request #23722 opened by pytorchbot
In progress gh/SS-JIA/659/orig
gh/SS-JIA/659/orig
In progress
[ET-VK][binary] Nest binary operator sources pull #97017: Pull request #23721 opened by pytorchbot
In progress gh/SS-JIA/658/orig
gh/SS-JIA/658/orig
In progress
[ET-VK][codegen] Support nested shader directories pull #97016: Pull request #23720 opened by pytorchbot
In progress gh/SS-JIA/657/orig
gh/SS-JIA/657/orig
In progress
[ET-VK][test] Allow FP16 underflow in SwiGLU comparisons pull #97015: Pull request #23719 opened by pytorchbot
In progress gh/SS-JIA/669/orig
gh/SS-JIA/669/orig
In progress
Insert write-back copy_ nodes at the earliest safe point pull #97014: Pull request #20744 synchronize by JPL11
Action required JPL11:early-write-back-copies
JPL11:early-write-back-copies
Action required
Fix pass ordering for sharded LLM export in QNN backend pull #97013: Pull request #23581 synchronize by SabYic
Action required SabYic:fix-qnn-sharded-pass-order
SabYic:fix-qnn-sharded-pass-order
Action required
Add CI integration for Spark-X2.5 models pull #97012: Pull request #23525 synchronize by dongjiang1989
Action required XHToken:support-spark2.5-ci
XHToken:support-spark2.5-ci
Action required
Fix pass ordering for sharded LLM export in QNN backend pull #97011: Pull request #23581 synchronize by SabYic
Action required SabYic:fix-qnn-sharded-pass-order
SabYic:fix-qnn-sharded-pass-order
Action required
[cuda] Check INT4 autotune decisions on ROCm without the CUDA-graph pick-quality bound pull #97010: Pull request #23642 synchronize by Gasoonjia
In progress gasoonjia/rocm-int4-autotune-pick-test
gasoonjia/rocm-int4-autotune-pick-test
In progress
[cuda] Score autotune picks with one event tick of tolerance, on longer kernels pull #97009: Pull request #23635 synchronize by Gasoonjia
In progress gasoonjia/autotune-regret-timer-resolution
gasoonjia/autotune-regret-timer-resolution
In progress
[QNN] Fix DiT checkpoint loading (#23718) pull #97008: Commit 068c08e pushed by rascani
In progress main
main
In progress
Insert write-back copy_ nodes at the earliest safe point pull #97007: Pull request #20744 synchronize by JPL11
Action required JPL11:early-write-back-copies
JPL11:early-write-back-copies
Action required
[cuda] Refresh the expired CUDA 13.4 torch nightly pin (#23713) pull #97006: Commit dfc4730 pushed by Gasoonjia
In progress main
main
In progress
feat: Re-inplace contiguous slice_copy as zero-copy memory.slice aliases (#10917) pull #97005: Pull request #21552 synchronize by iRAFEEK
Action required iRAFEEK:fix/reinplace-slice-copy
iRAFEEK:fix/reinplace-slice-copy
Action required
[cuda] Check INT4 autotune decisions on ROCm without the CUDA-graph pick-quality bound pull #97004: Pull request #23642 synchronize by Gasoonjia
54m 42s gasoonjia/rocm-int4-autotune-pick-test
gasoonjia/rocm-int4-autotune-pick-test
54m 42s
Raise inoperative error guards in ExportSession, XNNPACK node_visitor, and Samsung conv1d pull #97003: Pull request #22373 synchronize by AxelNoun
Action required AxelNoun:fix/unraised-error-checks
AxelNoun:fix/unraised-error-checks
Action required
Samsung Exynos AI LiteCore - Enable llama3.2 and gemma3 Models on AOT pull #97002: Pull request #23351 synchronize by Jiseong-oh
1h 36m 24s enable-llama-gemma3
enable-llama-gemma3
1h 36m 24s
Enable Spark-X2.5 export and runner support for MLX pull #97001: Pull request #23523 synchronize by metascroy
1h 39m 24s XHToken:add-spark2.5-mlx
XHToken:add-spark2.5-mlx
1h 39m 24s
[CoreML] Cache the quantizer's pattern graphs instead of rebuilding them per model pull #97000: Pull request #23323 synchronize by metascroy
1h 44m 37s vijay-kapse:perf/cache-coreml-quantizer-patterns
vijay-kapse:perf/cache-coreml-quantizer-patterns
1h 44m 37s
[CoreML] Cache the quantizer's pattern graphs instead of rebuilding them per model pull #96999: Pull request #23323 synchronize by metascroy
6m 7s vijay-kapse:perf/cache-coreml-quantizer-patterns
vijay-kapse:perf/cache-coreml-quantizer-patterns
6m 7s