Fp8 scaling per-sequence #79
Merged
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
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
Signed-off-by: Antoni Viros i Martin <aviros@ibm.com>
JRosenkranz
reviewed
Jul 17, 2025
| @@ -140,8 +140,8 @@ def generate( | |||
| from fms_mo.aiu_addons.fp8.fp8_utils import ScaledTensor | |||
| kwargs["past_key_value_states"] = [ | |||
| ( | |||
| ScaledTensor(torch.zeros(NUM_BLOCKS, BLOCK_SIZE, kvheads, head_size, dtype=torch.float8_e4m3fn), torch.tensor(1.0), False), | |||
| ScaledTensor(torch.zeros(NUM_BLOCKS, BLOCK_SIZE, kvheads, head_size, dtype=torch.float8_e4m3fn), torch.tensor(1.0), False), | |||
| ScaledTensor(torch.zeros(NUM_BLOCKS, BLOCK_SIZE, kvheads, head_size, dtype=torch.float8_e4m3fn), torch.tensor([1.0] * input_ids.shape[0], dtype=torch.float32), False), | |||
There was a problem hiding this comment.
why is the dtype torch.float32 here?
There was a problem hiding this comment.
FP8 scales are stored in fp32 always
|
bot:test |
|
bot:test |
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Outdated suggestions cannot be applied.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.
No description provided.