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
913 workflow runs
913 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

[cortex-m] Add scalar c++ op for dequantize_per_tensor Propose to merge ghstack orig PRs to main #463: Pull request #10267 closed by facebook-github-bot
53s gh/digantdesai/33/head
gh/digantdesai/33/head
53s
[cortex-m] Add scalar c++ op for quantize_per_tensor Propose to merge ghstack orig PRs to main #462: Pull request #10266 closed by facebook-github-bot
36s gh/digantdesai/32/head
gh/digantdesai/32/head
36s
[cortex-m] initial commit Propose to merge ghstack orig PRs to main #461: Pull request #10265 closed by facebook-github-bot
37s gh/digantdesai/31/head
gh/digantdesai/31/head
37s
[ET-VK] Add support for aten::upsample_bilinear2d ATen op Propose to merge ghstack orig PRs to main #460: Pull request #10306 closed by facebook-github-bot
34s gh/SS-JIA/216/head
gh/SS-JIA/216/head
34s
[ET-VK][ez] Store physical device identity metadata Propose to merge ghstack orig PRs to main #459: Pull request #10353 closed by facebook-github-bot
36s gh/SS-JIA/218/head
gh/SS-JIA/218/head
36s
[ET-VK][ez] Streamline + fix enabling device extensions Propose to merge ghstack orig PRs to main #458: Pull request #10352 closed by facebook-github-bot
36s gh/SS-JIA/217/head
gh/SS-JIA/217/head
36s
[Executorch][llama] Hookup use_attention_mask option in the source transforms inside llm mananger Propose to merge ghstack orig PRs to main #457: Pull request #10286 closed by facebook-github-bot
38s gh/kimishpatel/184/head
gh/kimishpatel/184/head
38s
[Executorch][llama] Allow custom sdpa op replacement pass to leverage attention mask Propose to merge ghstack orig PRs to main #456: Pull request #10285 closed by facebook-github-bot
34s gh/kimishpatel/183/head
gh/kimishpatel/183/head
34s
[Executorch][llama] bug fix for custom sdpa for attention bias Propose to merge ghstack orig PRs to main #455: Pull request #10284 closed by facebook-github-bot
44s gh/kimishpatel/182/head
gh/kimishpatel/182/head
44s
[Executorch][BE] Fix error logging with better message Propose to merge ghstack orig PRs to main #454: Pull request #10283 closed by facebook-github-bot
46s gh/kimishpatel/181/head
gh/kimishpatel/181/head
46s
Serialize PTD files with named data Propose to merge ghstack orig PRs to main #453: Pull request #10327 closed by facebook-github-bot
39s gh/lucylq/62/head
gh/lucylq/62/head
39s
Update module wrapper so that params are explicitly registered to the wrapper Propose to merge ghstack orig PRs to main #452: Pull request #10305 closed by facebook-github-bot
35s gh/lucylq/61/head
gh/lucylq/61/head
35s
Refactor export_delegated_program Propose to merge ghstack orig PRs to main #451: Pull request #10303 closed by facebook-github-bot
37s gh/lucylq/60/head
gh/lucylq/60/head
37s
[mps] Disable dialect verifier under mps preprocess Propose to merge ghstack orig PRs to main #450: Pull request #10276 closed by facebook-github-bot
35s gh/digantdesai/36/head
gh/digantdesai/36/head
35s
[exir] Allow verifiers in _transform Propose to merge ghstack orig PRs to main #449: Pull request #10274 closed by facebook-github-bot
38s gh/digantdesai/34/head
gh/digantdesai/34/head
38s
[ET-VK] Use performant tiled algorithm for 4 bit weight only quantized linear Propose to merge ghstack orig PRs to main #448: Pull request #10205 closed by facebook-github-bot
38s gh/SS-JIA/213/head
gh/SS-JIA/213/head
38s
[ET-VK][ez] Add support for buffer backed qparams in int4 linear + add checks for physical limits when allocating Propose to merge ghstack orig PRs to main #447: Pull request #9974 closed by facebook-github-bot
51s gh/SS-JIA/209/head
gh/SS-JIA/209/head
51s
[ET-VK] Add co-op algorithm for 4 bit weight only quantized linear Propose to merge ghstack orig PRs to main #446: Pull request #10204 closed by facebook-github-bot
34s gh/SS-JIA/212/head
gh/SS-JIA/212/head
34s
[ET-VK] Allow int4 linear to execute without 8bit buffer support Propose to merge ghstack orig PRs to main #445: Pull request #10030 closed by facebook-github-bot
39s gh/SS-JIA/210/head
gh/SS-JIA/210/head
39s
[0.6 documentation] Fix Page Developer Tools: Bundled Program Propose to merge ghstack orig PRs to main #444: Pull request #10194 closed by zhenyan-zhang-meta
35s gh/zhenyan-zhang-meta/3/head
gh/zhenyan-zhang-meta/3/head
35s
[ET-VK][ez] Support convolutions with padding > 0 and dilation > 1 Propose to merge ghstack orig PRs to main #443: Pull request #10115 closed by facebook-github-bot
35s gh/SS-JIA/211/head
gh/SS-JIA/211/head
35s
[#9971] Gracefully error out in ETDump for get_flatbuffer_scalar_type Propose to merge ghstack orig PRs to main #442: Pull request #10056 closed by facebook-github-bot
33s gh/zhenyan-zhang-meta/2/head
gh/zhenyan-zhang-meta/2/head
33s
[Executorch][llama] Enable quantized sdpa Propose to merge ghstack orig PRs to main #441: Pull request #9945 closed by facebook-github-bot
54s gh/kimishpatel/172/head
gh/kimishpatel/172/head
54s
[Executorch][llama] Renamed quantized_kv_cache to custom_kv_cache Propose to merge ghstack orig PRs to main #440: Pull request #9944 closed by facebook-github-bot
1m 0s gh/kimishpatel/171/head
gh/kimishpatel/171/head
1m 0s
[Executorch][SDPA] Refactor + Make quantized sdpa handle sequence at dim 1 or 2 Propose to merge ghstack orig PRs to main #439: Pull request #9943 closed by facebook-github-bot
55s gh/kimishpatel/170/head
gh/kimishpatel/170/head
55s
ProTip! You can narrow down the results and go further in time using created:<2025-04-10 or the other filters available.