Add support for quantized bmm #4047
Closed
Conversation
This file contains 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/4047
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ✅ You can merge normally! (1 Unrelated Failure)As of commit 49950a9 with merge base 63e8025 ( BROKEN TRUNK - The following job failed but were 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. |
facebook-github-bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D58959269 |
|
This pull request was exported from Phabricator. Differential Revision: D58959269 |
mcremon-meta
added a commit
that referenced
this pull request
Jun 26, 2024
Summary: Pull Request resolved: #4047 The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well. Differential Revision: D58959269
mcremon-meta
force-pushed
the
export-D58959269
branch
from
59f03b6
to
92cab3c
Compare
facebook-github-bot
pushed a commit
that referenced
this pull request
Jul 10, 2024
Summary: The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well. Use a decomposition for SDPA to make sure LLaMa bmms get quantized. Differential Revision: D58959269
mcremon-meta
pushed a commit
that referenced
this pull request
Jul 10, 2024
Summary: Pull Request resolved: #4047 The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well. Use a decomposition for SDPA to make sure LLaMa bmms get quantized. Differential Revision: D58959269
mcremon-meta
pushed a commit
that referenced
this pull request
Jul 10, 2024
Summary: Pull Request resolved: #4047 The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well. Use a decomposition for SDPA to make sure LLaMa bmms get quantized. Differential Revision: D58959269 Reviewed By: zonglinpengmeta, hsharma35
facebook-github-bot
pushed a commit
that referenced
this pull request
Jul 11, 2024
Summary: The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well. Use a decomposition for SDPA to make sure LLaMa bmms get quantized. Reviewed By: zonglinpengmeta, hsharma35 Differential Revision: D58959269
facebook-github-bot
force-pushed
the
export-D58959269
branch
from
92cab3c
to
a83f95e
Compare
|
This pull request was exported from Phabricator. Differential Revision: D58959269 |
Summary: Pull Request resolved: #4047 The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well Reviewed By: zonglinpengmeta, hsharma35 Differential Revision: D58959269
|
This pull request was exported from Phabricator. Differential Revision: D58959269 |
mcremon-meta
force-pushed
the
export-D58959269
branch
from
a83f95e
to
49950a9
Compare
zonglinpengmeta
approved these changes
Jul 11, 2024
| @@ -28,6 +28,7 @@ python_library( | |||
| "compiler.py", | |||
| ], | |||
| deps = [ | |||
| "fbsource//third-party/pypi/pyre-extensions:pyre-extensions", | |||
There was a problem hiding this comment.
Is Buck target used here or meant not to export?
There was a problem hiding this comment.
OSS uses both buck and CMake I believe for now
dulinriley
approved these changes
Jul 11, 2024
| @@ -28,6 +28,7 @@ python_library( | |||
| "compiler.py", | |||
| ], | |||
| deps = [ | |||
| "fbsource//third-party/pypi/pyre-extensions:pyre-extensions", | |||
There was a problem hiding this comment.
OSS uses both buck and CMake I believe for now
facebook-github-bot
pushed a commit
that referenced
this pull request
Jul 12, 2024
Summary: The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for `torch.bmm` as well Reviewed By: dulinriley, zonglinpengmeta, hsharma35 Differential Revision: D58959269
|
This pull request has been merged in cfbe63d. |
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: The current quantizer only captures "fake" bmm from matmuls with specific shapes. Add support for
torch.bmmas well.Differential Revision: D58959269