symmetric quantization to FBGEMM prefill token-wise FP8 (fixed) #4868
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
✅ Deploy Preview for pytorch-fbgemm-docs ready!
To edit notification comments on pull requests, go to your Netlify project configuration. |
|
@ColinPeppler has exported this pull request. If you are a Meta employee, you can view the originating diff in D82320500. |
…rch#4868) Summary: X-link: facebookresearch/FBGEMM#1890 Differential Revision: D82320500
ColinPeppler
force-pushed
the
export-D82320500
branch
from
5eb9f4c to
323989a
Compare
|
@ColinPeppler has exported this pull request. If you are a Meta employee, you can view the originating diff in D82320500. |
ColinPeppler
added a commit
to ColinPeppler/FBGEMM
that referenced
this pull request
Sep 18, 2025
…rch#4868) Summary: X-link: facebookresearch/FBGEMM#1890 Differential Revision: D82320500
ColinPeppler
added a commit
to ColinPeppler/FBGEMM
that referenced
this pull request
Sep 18, 2025
…rch#4868) Summary: X-link: facebookresearch/FBGEMM#1890 Differential Revision: D82320500
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Outdated suggestions cannot be applied.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:
What
Llama numerical issue fix
In the original diff, I was not checking the value of
std::optional<bool> symmetriconly that a value existed...https://www.internalfb.com/code/fbsource/[e97b4a76367b61af327d1aa2683d691730220493]/fbcode/deeplearning/fbgemm/fbgemm_gpu/experimental/gen_ai/src/kv_cache/kv_cache.cu?lines=2903%2C2911%2C2981-2982
This is now fixed with
Differential Revision: D82320500