Add NANOO FP8 Support #2695
Open
Add NANOO FP8 Support #2695
+655
−111
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
ScXfjiang
force-pushed
the
dev_nanoo_fp8
branch
from
7c84244
to
77f6214
Compare
ScXfjiang
force-pushed
the
dev_nanoo_fp8
branch
from
6aa7078
to
8ecf02f
Compare
| @@ -563,6 +563,14 @@ struct ProtoHelper<float8_e5m2> : public Float8ProtoHelper<float8_e5m2> {}; | |||
| template <> | |||
| struct ProtoHelper<float8_e4m3fn> : public Float8ProtoHelper<float8_e4m3fn> {}; | |||
|
|
|||
| template <> | |||
There was a problem hiding this comment.
Nit: Format the code the same way as that for ocp fp8?
There was a problem hiding this comment.
I believe it's auto-formatted by clang-format.
https://github.com/ROCm/tensorflow-upstream/blob/develop-upstream/tensorflow/.clang-format
| @@ -271,8 +271,8 @@ def testBfloat16(self): | |||
| def testFloat8e5m2(self): | |||
| test_type = dtypes.float8_e5m2.as_numpy_dtype | |||
| t = tensor_util.make_tensor_proto(np.array([10.0, 20.0], dtype=test_type)) | |||
| # 10.0: "I" = 73 = 10010 01: 2^(18 - 15) * (1 + 1/4) | |||
| # 20.0: "M" = 77 = 10011 01: 2^(19 - 15) * (1 + 1/4) | |||
| # 10.0: "I" = 73 = 0 10010 01: 2^(18 - 15) * (1 + 1/4) | |||
There was a problem hiding this comment.
Nit: Why do we need the extra 0 here? For more clarity?
There was a problem hiding this comment.
Updated. (I just wanted to display all bit positions of FP8. But I agree that our repo should be consistent with the upstream repo as possible as we can, for less pain in the weekly sync.)
Add NANOO FP8 Support To OPs
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Outdated suggestions cannot be applied.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.
This PR adds
tf.experimental.float8_e4m3fnuzandtf.experimental.float8_e5m2fnuzas public tensorflow data types.similar work: