-
-
Notifications
You must be signed in to change notification settings - Fork 4.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
support bitsandbytes 8-bit and FP4 quantized models #7445
Merged
Merged
Changes from 6 commits
Commits
Show all changes
8 commits
Select commit
Hold shift + click to select a range
450ae2a
support bitsandbytes 8-bit and FP4 quantized models
chenqianfzh a2da808
fix tests etc
chenqianfzh 141d437
Merge branch 'main' into bnb-8bit
chenqianfzh 26180ef
Merge branch 'main' into bnb-8bit
chenqianfzh cad394d
Merge branch 'main' into bnb-8bit
chenqianfzh 11c07d4
Merge branch 'main' into bnb-8bit
chenqianfzh c6fb4e0
WIP
chenqianfzh 368ce90
simplify the test to cut memory print
chenqianfzh File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
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
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
Oops, something went wrong.
Oops, something went wrong.
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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
bitsandbytes-foundation/bitsandbytes#1330 has been merged. Regarding these tests, can we now use cudagraph?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Hi, @jeejeelee, thanks to your fix in bnb.
But the latest version of bnb package was released three weeks ago, which does not include your fix yet.
I will update the code after the next bnb release is out.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Agreed, I think it is worth doing the package upgrade in another PR
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
It seems that this PR introduces a new BNB kernel . I'm not sure if the previous modifications to BNB can support this kernel. What I mean is, perhaps we should first verify this (build BNB from source). If this kernel still not supported, we may need to continue refining the relevant BNB code.
If you're not available, I can verify it next week.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
@jeejeelee
I tried the new bnb kernel with your fix to run the above tests under graph mode (and some other tests), it worked perfectly! :-)