Support nvidia16 GPUs #292
Merged
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
|
Excellent, thank you so much for this PR! |
borzunov
added a commit
to bigscience-workshop/petals
that referenced
this pull request
Apr 12, 2023
In particular, this PR fixes 8-bit support on nvidia16 GPUs (such as 1660) by including bitsandbytes-foundation/bitsandbytes#292. This support was requested multiple times on Discord.
Closed
1 task
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Outdated suggestions cannot be applied.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.
There is a set of GPUs that are technically Turing, but they lack tensor cores and some other Turing features. Turns out, they are fairly popular and people host 3-5B models on those cards. This PR makes them compatible with load_in_8bit.