[varlen_attn for inference] remove unnecessary tensor creation#176723
[varlen_attn for inference] remove unnecessary tensor creation#176723liangel-02 wants to merge 7 commits intogh/liangel-02/18/basefrom
Conversation
[ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/176723
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit c9ed5a1 with merge base 4bc9d7f ( FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
This PR needs a
|
| alibi_slopes: torch.Tensor | None = None, | ||
| out: torch.Tensor | None = None, | ||
| block_table: torch.Tensor | None = None, | ||
| compute_auxiliary: bool = True, |
There was a problem hiding this comment.
This smells like Boolean trap... do we need to add this for every other sdpa derivative?
There was a problem hiding this comment.
this is private impl so should be fine and it is specific to varlen API. Once we get fa4 wired up we should probably do teh same
|
@pytorchbot merge -i |
Merge startedYour change will be merged while ignoring the following 2 checks: trunk / win-vs2022-cpu-py3 / build, trunk / win-vs2022-cuda12.8-py3 / build Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
|
The merge job was canceled or timed out. This most often happen if two merge requests were issued for the same PR, or if merge job was waiting for more than 6 hours for tests to finish. In later case, please do not hesitate to reissue the merge command |
|
@pytorchbot merge -i |
Merge startedYour change will be merged while ignoring the following 1 checks: trunk / macos-py3-arm64 / test (mps, 1, 1, macos-m2-15) Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
#176723)" This reverts commit c405acd. Reverted #176723 on behalf of https://github.com/zou3519 due to sorry I think this broke inductor rocm ([comment](#175897 (comment)))
|
@liangel-02 your PR has been reverted as part of the stack under #175897. |
|
@liangel-02 your PR has been reverted as part of the stack under #175924. |
#176723)" This reverts commit 26dddb9. Reverted #176723 on behalf of https://github.com/huydhn due to Sorry for reverting your change but a bunch of internal builds need to be updated to unblock this change D95758397 ([comment](#175924 (comment)))
…tion" [ghstack-poisoned]
…tion" [ghstack-poisoned]
…tion" [ghstack-poisoned]
|
@liangel-02 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
…tion" Differential Revision: [D95996397](https://our.internmc.facebook.com/intern/diff/D95996397) [ghstack-poisoned]
Pull Request resolved: #176723 @imported-using-ghimport Differential Revision: [D95996397](https://our.internmc.facebook.com/intern/diff/D95996397/) ghstack-source-id: 350342133
…tion" Differential Revision: [D95996397](https://our.internmc.facebook.com/intern/diff/D95996397) [ghstack-poisoned]
|
@pytorchbot merge -f "ignoring meta internal-only changes check" cc @huydhn |
|
❌ 🤖 pytorchbot command failed: Try |
|
@pytorchbot merge -f "ignoring meta internal-only changes check" |
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Merge failedReason: This PR has internal changes and must be landed via Phabricator! Please try reimporting/rexporting the PR! Details for Dev Infra teamRaised by workflow job |
|
@pytorchbot merge -f 'Ignoring meta internal-only changes check' |
Merge startedYour change will be merged immediately since you used the force (-f) flag, bypassing any CI checks (ETA: 1-5 minutes). Please use Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Stack from ghstack (oldest at bottom):