Add a bf16 datatype to sfnp #914
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
KyleHerndon
changed the title
|
We determined the numerical issue is elsewhere. This is ready for review. |
KyleHerndon
changed the title
monorimet
approved these changes
Feb 12, 2025
monorimet
pushed a commit
that referenced
this pull request
Feb 13, 2025
Add bf16 datatype, functions, and tests
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Outdated suggestions cannot be applied.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.
I don't fully understand the surrounding code, but I made this thin wrapper and it seems to mostly work. Let me know if you see any glaring issues, because I'm debugging Flux BF16 on top of this and can't pinpoint the issue.
It probably makes sense to move the type definition to another file, I was just hacking on it. Trying to figure out where things belong too.
(For reference I tried working with the __bf16 clang type, but it didn't have enough support so I decided to make this from scratch/uint16 instead)