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] Plumb subgroup property queries + VK_EXT_subgroup_size_control Propose to merge ghstack orig PRs to main #1182: Pull request #19403 closed by meta-codesync Bot
44s gh/SS-JIA/530/head
gh/SS-JIA/530/head
44s
[ET-VK] Make libtorch optional in custom op test binaries Propose to merge ghstack orig PRs to main #1181: Pull request #19402 closed by meta-codesync Bot
1m 0s gh/SS-JIA/529/head
gh/SS-JIA/529/head
1m 0s
Remove benchmark scripts from git tracking Propose to merge ghstack orig PRs to main #1180: Pull request #19189 closed by digantdesai
42s gh/digantdesai/52/head
gh/digantdesai/52/head
42s
Add structured stats reporting and GPU memory tracking to Qwen3.5 MoE runner Propose to merge ghstack orig PRs to main #1179: Pull request #19190 closed by digantdesai
52s gh/digantdesai/53/head
gh/digantdesai/53/head
52s
Add Triton INT4 dense kernels with dequant prefill path for Qwen3.5 MoE Propose to merge ghstack orig PRs to main #1178: Pull request #19188 closed by digantdesai
50s gh/digantdesai/51/head
gh/digantdesai/51/head
50s
Add W4A8 INT8 activation kernels for batched MoE prefill Propose to merge ghstack orig PRs to main #1177: Pull request #19187 closed by digantdesai
55s gh/digantdesai/50/head
gh/digantdesai/50/head
55s
[ET-VK] Add apply_rotary_emb_interleaved fused operator Propose to merge ghstack orig PRs to main #1176: Pull request #19115 closed by meta-codesync Bot
42s gh/SS-JIA/524/head
gh/SS-JIA/524/head
42s
[ET-VK] Update fused SDPA operator to support ViT attention Propose to merge ghstack orig PRs to main #1175: Pull request #19114 closed by meta-codesync Bot
55s gh/SS-JIA/523/head
gh/SS-JIA/523/head
55s
[ET-VK] Prefer downstream layout in TagMemoryMetaPass to reduce transitions Propose to merge ghstack orig PRs to main #1174: Pull request #19113 closed by meta-codesync Bot
56s gh/SS-JIA/522/head
gh/SS-JIA/522/head
56s
Use safe_numel() in et Propose to merge ghstack orig PRs to main #1173: Pull request #19075 closed by meta-codesync Bot
45s gh/lucylq/155/head
gh/lucylq/155/head
45s
Use compute_numel_overflow() in tensor_ptr builders Propose to merge ghstack orig PRs to main #1172: Pull request #19076 closed by lucylq
38s gh/lucylq/156/head
gh/lucylq/156/head
38s
[ExecuTorch][Llama][ez] Remove unwrap_tensor_subclass from 4w quantization path Propose to merge ghstack orig PRs to main #1171: Pull request #18957 closed by meta-codesync Bot
45s gh/SS-JIA/521/head
gh/SS-JIA/521/head
45s
[ET Device Support] Parse device info from serialized tensor in tensor_parser Propose to merge ghstack orig PRs to main #1170: Pull request #18328 closed by Gasoonjia
50s gh/gasoonjia/143/head
gh/gasoonjia/143/head
50s
[ET-VK] Fix use-after-free in PrepackNode when TensorRefs are shared Propose to merge ghstack orig PRs to main #1169: Pull request #18906 closed by meta-codesync Bot
50s gh/SS-JIA/520/head
gh/SS-JIA/520/head
50s
[ET Device Support] Propagate device info from TensorSpec into serialized Tensor Propose to merge ghstack orig PRs to main #1168: Pull request #18079 closed by Gasoonjia
50s gh/gasoonjia/136/head
gh/gasoonjia/136/head
50s
[executorch] Propagate device metadata from partitioner result onto TensorSpecs Propose to merge ghstack orig PRs to main #1167: Pull request #18078 closed by Gasoonjia
54s gh/gasoonjia/135/head
gh/gasoonjia/135/head
54s
[ET-VK] Lower reduce_peak_memory threshold from 500 MB to 10 MB Propose to merge ghstack orig PRs to main #1166: Pull request #18816 closed by meta-codesync Bot
50s gh/SS-JIA/519/head
gh/SS-JIA/519/head
50s
[ET-VK] Add etvk.use_existing_vma config to avoid duplicate VMA symbols Propose to merge ghstack orig PRs to main #1165: Pull request #18522 closed by meta-codesync Bot
47s gh/SS-JIA/512/head
gh/SS-JIA/512/head
47s
[ET-VK] Fused RMSNorm operator to fix fp16 overflow Propose to merge ghstack orig PRs to main #1164: Pull request #18772 closed by meta-codesync Bot
48s gh/SS-JIA/518/head
gh/SS-JIA/518/head
48s
[ET-VK] Deduplicate transition clone nodes in TagMemoryMetaPass Propose to merge ghstack orig PRs to main #1163: Pull request #18771 closed by meta-codesync Bot
46s gh/SS-JIA/517/head
gh/SS-JIA/517/head
46s
[ET-VK] Fix force_fp16 texture bias being silently rejected for CONTIGUOUS_ANY ops Propose to merge ghstack orig PRs to main #1162: Pull request #18770 closed by meta-codesync Bot
48s gh/SS-JIA/516/head
gh/SS-JIA/516/head
48s
make to_edge support etrecord generation Propose to merge ghstack orig PRs to main #1161: Pull request #13151 closed by Gasoonjia
37s gh/gasoonjia/37/head
gh/gasoonjia/37/head
37s
[ET-VK] Fix pack_fp_linear_weight for devices without VK_KHR_16bit_storage Propose to merge ghstack orig PRs to main #1160: Pull request #18642 closed by meta-codesync Bot
43s gh/SS-JIA/515/head
gh/SS-JIA/515/head
43s
[ET-VK] Add fused HuggingFace RoPE operator (apply_rotary_emb_hf) Propose to merge ghstack orig PRs to main #1159: Pull request #18592 closed by meta-codesync Bot
39s gh/SS-JIA/514/head
gh/SS-JIA/514/head
39s
[ET-VK] Fix embedding_q4gsw out-of-bounds access with dynamic shapes Propose to merge ghstack orig PRs to main #1158: Pull request #18558 closed by meta-codesync Bot
45s gh/SS-JIA/513/head
gh/SS-JIA/513/head
45s