Eliminate MemCpyDtoH overhead for quantized fast_gemv kernel #3725
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 pull request was exported from Phabricator. Differential Revision: D70072967 |
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify site configuration. |
YUNQIUGUO
added a commit
to YUNQIUGUO/FBGEMM
that referenced
this pull request
Feb 24, 2025
…#3725) Summary: X-link: facebookresearch/FBGEMM#808 As title. Previously `w_scale.item()` will create unnecessary DeviceToHost memcpy operations thus introduces big gaps in between each gemv kernel launch call {F1975359276} Fixed in this diff and other minor updates. Differential Revision: D70072967
YUNQIUGUO
added a commit
to YUNQIUGUO/FBGEMM
that referenced
this pull request
Feb 24, 2025
…#3725) Summary: X-link: facebookresearch/FBGEMM#808 As title. Previously `w_scale.item()` will create unnecessary DeviceToHost memcpy operations thus introduces big gaps in between each gemv kernel launch call {F1975359276} Fixed in this diff and other minor updates. Differential Revision: D70072967
YUNQIUGUO
force-pushed
the
export-D70072967
branch
2 times, most recently
from
25b2d7a to
74981f7
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70072967 |
YUNQIUGUO
force-pushed
the
export-D70072967
branch
from
74981f7 to
25b2d7a
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70072967 |
…#3725) Summary: X-link: facebookresearch/FBGEMM#808 As title. Previously `w_scale.item()` will create unnecessary DeviceToHost memcpy operations thus introduces big gaps in between each gemv kernel launch call {F1975359276} Fixed in this diff and other minor updates. Differential Revision: D70072967
YUNQIUGUO
force-pushed
the
export-D70072967
branch
from
25b2d7a to
2ec1051
Compare
|
This pull request was exported from Phabricator. Differential Revision: D70072967 |
|
This pull request has been merged in 1529564. |
q10
pushed a commit
to q10/FBGEMM
that referenced
this pull request
Apr 10, 2025
…#808) Summary: X-link: pytorch#3725 Pull Request resolved: facebookresearch/FBGEMM#808 As title. Previously `w_scale.item()` will create unnecessary DeviceToHost memcpy operations thus introduces big gaps in between each gemv kernel launch call {F1975359276} Fixed in this diff and other minor updates. Reviewed By: ipiszy Differential Revision: D70072967 fbshipit-source-id: f71c838943ea45bc07041ba64426c13e995ff93d
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:
X-link: https://github.com/facebookresearch/FBGEMM/pull/808
As title.
Previously
w_scale.item()will create unnecessary DeviceToHost memcpy operations thus introduces big gaps in between each gemv kernel launch call{F1975359276}
Fixed in this diff and other minor updates.
Differential Revision: D70072967