Support fp8 direct quantization #69
Open
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
|
Does this PR depend on Flex PRhttps://github.com/google/flax/pull/3922? |
Yes, it does. We need to first merge the flax one before working on this one. |
wenscarl
force-pushed
the
fp8_direct_quant
branch
2 times, most recently
from
71abfaf
to
9509995
Compare
kaixih
reviewed
Aug 30, 2024
kaixih
approved these changes
Aug 30, 2024
Call quantized_einsum
wenscarl
force-pushed
the
fp8_direct_quant
branch
from
a15bfe1
to
8cbcf50
Compare
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Outdated suggestions cannot be applied.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.
Support fp8 direct quantization. ref. the merged Flex PR3922 and now depends on Flax PR4229
cc @kaixih @zhangqiaorjc