Enable SDPA without kv cache #8950
Open
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/8950
Note: Links to docs will display an error until the docs builds have been completed. ❌ 4 New FailuresAs of commit d6cf34e with merge base f6c5959 ( NEW FAILURES - The following jobs have failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
iseeyuan
force-pushed
the
export-D70593177
branch
from
12f83ab to
354159e
Compare
|
@pytorchbot label "topic: not user facing" |
jackzhxng
approved these changes
Mar 5, 2025
iseeyuan
force-pushed
the
export-D70593177
branch
from
354159e to
d804e5c
Compare
iseeyuan
pushed a commit
to iseeyuan/executorch-1
that referenced
this pull request
Mar 7, 2025
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
iseeyuan
pushed a commit
to iseeyuan/executorch-1
that referenced
this pull request
Mar 7, 2025
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
iseeyuan
force-pushed
the
export-D70593177
branch
from
d804e5c to
eda8111
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
iseeyuan
pushed a commit
to iseeyuan/executorch-1
that referenced
this pull request
Mar 7, 2025
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
iseeyuan
force-pushed
the
export-D70593177
branch
from
eda8111 to
627609e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
iseeyuan
pushed a commit
to iseeyuan/executorch-1
that referenced
this pull request
Mar 7, 2025
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
iseeyuan
force-pushed
the
export-D70593177
branch
from
627609e to
809f578
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
Summary: Pull Request resolved: pytorch#8950 Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
iseeyuan
force-pushed
the
export-D70593177
branch
from
809f578 to
2fee7ce
Compare
iseeyuan
pushed a commit
to iseeyuan/executorch-1
that referenced
this pull request
Mar 7, 2025
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache. Reviewed By: kimishpatel Differential Revision: D70593177
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
1 similar comment
|
This pull request was exported from Phabricator. Differential Revision: D70593177 |
iseeyuan
force-pushed
the
export-D70593177
branch
from
2fee7ce to
d6cf34e
Compare
This was referenced Mar 17, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Summary: Sdpa custom op has been decoupled from kv cache by kimishpatel. Update the llama definition so that the sdpa op is applied both with and without kv cache.
Differential Revision: D70593177