{executorch][llama] support mqa #3080
Closed
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
This diff adds support for multi query attention for sdpa with kv cache Differential Revision: [D56228316](https://our.internmc.facebook.com/intern/diff/D56228316/) [ghstack-poisoned]
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/3080
Note: Links to docs will display an error until the docs builds have been completed. ❌ 5 New FailuresAs of commit 26aced7 with merge base 458d743 ( 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: D56228316 |
kimishpatel
added a commit
that referenced
this pull request
Apr 17, 2024
This diff adds support for multi query attention for sdpa with kv cache Differential Revision: [D56228316](https://our.internmc.facebook.com/intern/diff/D56228316/) ghstack-source-id: 222819128 Pull Request resolved: #3080
mikekgfb
approved these changes
Apr 17, 2024
| @@ -1,8 +1,22 @@ | |||
| # Any targets that should be shared between fbcode and xplat must be defined in | |||
| # targets.bzl. This file can contain fbcode-only targets. | |||
|
|
|||
| load("@fbcode_macros//build_defs:python_unittest.bzl", "python_unittest") | |||
There was a problem hiding this comment.
Use runtime? You can do
runtime.python_unittest(
...
)
There was a problem hiding this comment.
oh this was due to arc lint. let me fix.
This diff adds support for multi query attention for sdpa with kv cache Differential Revision: [D56228316](https://our.internmc.facebook.com/intern/diff/D56228316/) [ghstack-poisoned]
kimishpatel
added a commit
that referenced
this pull request
Apr 17, 2024
Pull Request resolved: #3080 This diff adds support for multi query attention for sdpa with kv cache Differential Revision: [D56228316](https://our.internmc.facebook.com/intern/diff/D56228316/) ghstack-source-id: 222855405
|
This pull request was exported from Phabricator. Differential Revision: D56228316 |
|
bunch of pre-existing failures with re2.h that @larryliu0820 is fixing |
|
This pull request has been merged in bae0387. |
Closed
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.
Stack from ghstack (oldest at bottom):
This diff adds support for multi query attention for sdpa with kv cache
Differential Revision: D56228316