Skip to content

Actions: pytorch/executorch

Actions

Propose to merge ghstack orig PRs to main

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
ghstack_land.yml
783 workflow runs
783 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
[ET-VK][conv1d] Route conv1d to height-packed implementations in export pipeline Propose to merge ghstack orig PRs to main #1157: Pull request #18334 closed by meta-codesync Bot
45s gh/SS-JIA/496/head
gh/SS-JIA/496/head
45s
[ET-VK][conv1d] Implement height-packed depthwise conv1d operator Propose to merge ghstack orig PRs to main #1156: Pull request #18333 closed by meta-codesync Bot
52s gh/SS-JIA/495/head
gh/SS-JIA/495/head
52s
[ET-VK][conv1d] Implement height-packed pointwise conv1d operator Propose to merge ghstack orig PRs to main #1155: Pull request #18332 closed by meta-codesync Bot
48s gh/SS-JIA/494/head
gh/SS-JIA/494/head
48s
Make multimethod generic in llm_config Propose to merge ghstack orig PRs to main #1154: Pull request #18213 closed by meta-codesync Bot
40s gh/lucylq/140/head
gh/lucylq/140/head
40s
[ET-VK] Replace dynamic UBO indexing with safe_idx across shaders Propose to merge ghstack orig PRs to main #1153: Pull request #18512 closed by meta-codesync Bot
45s gh/SS-JIA/511/head
gh/SS-JIA/511/head
45s
[ET-VK] Modernize permute op with safe indexing and unified dispatch Propose to merge ghstack orig PRs to main #1152: Pull request #18511 closed by meta-codesync Bot
47s gh/SS-JIA/510/head
gh/SS-JIA/510/head
47s
[ET-VK] Support alias_copy in partitioner by removing it as a redundant op Propose to merge ghstack orig PRs to main #1145: Pull request #18408 closed by meta-codesync Bot
46s gh/SS-JIA/501/head
gh/SS-JIA/501/head
46s
[ET-VK][sdpa] Use numerically-stable softmax in attention weights Propose to merge ghstack orig PRs to main #1144: Pull request #18407 closed by meta-codesync Bot
42s gh/SS-JIA/500/head
gh/SS-JIA/500/head
42s
[ET Device Support] TensorImpl carries device info Propose to merge ghstack orig PRs to main #1143: Pull request #17534 closed by meta-codesync Bot
42s gh/gasoonjia/123/head
gh/gasoonjia/123/head
42s
Improve QNN backend build-from-source user experience Propose to merge ghstack orig PRs to main #1142: Pull request #17990 closed by abhinaykukkadapu
44s gh/abhinaykukkadapu/17/head
gh/abhinaykukkadapu/17/head
44s
Improve QNN backend AOT user experience Propose to merge ghstack orig PRs to main #1141: Pull request #17989 closed by abhinaykukkadapu
50s gh/abhinaykukkadapu/16/head
gh/abhinaykukkadapu/16/head
50s
[ET Device Support] Schema changes: device info on Tensor and buffer-level device array Propose to merge ghstack orig PRs to main #1140: Pull request #17533 closed by meta-codesync Bot
47s gh/gasoonjia/122/head
gh/gasoonjia/122/head
47s
[ET-VK][runtime] Add prepack cache to avoid duplicate weight prepacking Propose to merge ghstack orig PRs to main #1139: Pull request #18361 closed by SS-JIA
39s gh/SS-JIA/499/head
gh/SS-JIA/499/head
39s
[ET-VK][conv2d_dw] Extract depthwise dispatch into Conv2dDW.cpp with device-based tile selection Propose to merge ghstack orig PRs to main #1138: Pull request #18293 closed by meta-codesync Bot
45s gh/SS-JIA/493/head
gh/SS-JIA/493/head
45s
[ET-VK][conv2d] Re-implement pointwise conv2d with tiled compute and blocked weight packing Propose to merge ghstack orig PRs to main #1137: Pull request #18292 closed by meta-codesync Bot
2m 5s gh/SS-JIA/492/head
gh/SS-JIA/492/head
2m 5s
[ET-VK] Fix staging buffer allocation to check all memory types for HOST_CACHED Propose to merge ghstack orig PRs to main #1136: Pull request #18291 closed by meta-codesync Bot
49s gh/SS-JIA/491/head
gh/SS-JIA/491/head
49s
[ET-VK][qlinear] Add bias support to q4gsw and dq8ca_q4gsw quantized linear ops Propose to merge ghstack orig PRs to main #1135: Pull request #18061 closed by meta-codesync Bot
1m 11s gh/SS-JIA/478/head
gh/SS-JIA/478/head
1m 11s
[ET-VK] Implement missing Vulkan operators for Parakeet TDT model Propose to merge ghstack orig PRs to main #1134: Pull request #18059 closed by meta-codesync Bot
1m 11s gh/SS-JIA/476/head
gh/SS-JIA/476/head
1m 11s
[ET-VK] Add ANY_STORAGE support to argmax and argmin Propose to merge ghstack orig PRs to main #1133: Pull request #18058 closed by meta-codesync Bot
1m 7s gh/SS-JIA/475/head
gh/SS-JIA/475/head
1m 7s
[ET-VK] Add ANY_STORAGE support to embedding Propose to merge ghstack orig PRs to main #1132: Pull request #18057 closed by meta-codesync Bot
1m 16s gh/SS-JIA/474/head
gh/SS-JIA/474/head
1m 16s
[ET-VK] Add ANY_STORAGE support to repeat Propose to merge ghstack orig PRs to main #1131: Pull request #18056 closed by meta-codesync Bot
1m 22s gh/SS-JIA/473/head
gh/SS-JIA/473/head
1m 22s
[ET-VK] Add ANY_STORAGE support to native_layer_norm Propose to merge ghstack orig PRs to main #1130: Pull request #18055 closed by meta-codesync Bot
1m 22s gh/SS-JIA/472/head
gh/SS-JIA/472/head
1m 22s
[ET-VK] Add ANY_STORAGE support to softmax and log_softmax Propose to merge ghstack orig PRs to main #1129: Pull request #18054 closed by meta-codesync Bot
1m 14s gh/SS-JIA/471/head
gh/SS-JIA/471/head
1m 14s
[ET-VK] Add ANY_STORAGE support to expand_copy Propose to merge ghstack orig PRs to main #1128: Pull request #18053 closed by meta-codesync Bot
1m 13s gh/SS-JIA/470/head
gh/SS-JIA/470/head
1m 13s
[ET-VK] Add ANY_STORAGE support to arange and full Propose to merge ghstack orig PRs to main #1127: Pull request #18052 closed by meta-codesync Bot
1m 6s gh/SS-JIA/469/head
gh/SS-JIA/469/head
1m 6s