Skip to content

[not for land] testing out float8 128_1_128_128 blockwise scaling #1317

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 1 commit into
base: main
Choose a base branch
from
Open

[not for land] testing out float8 128_1_128_128 blockwise scaling #1317

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions torchtitan/components/quantization/float8.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -101,6 +101,19 @@ def convert(self, model: nn.Module):
if not self.enabled:
return

from torchao.quantization import quantize_
from torchao.prototype.deep_gemm_float8_training.linear import (
DeepGemmFloat8LinearConfig,
)

quantize_(
model,
config=DeepGemmFloat8LinearConfig(),
filter_fn=lambda mod, fqn: isinstance(mod, torch.nn.Linear) and fqn != "output",
)
logger.info("enabled DeepGemm dense training")
return

from torchao.float8 import convert_to_float8_training

# Mutates the model inplace replacing instances of nn.Linear with Float8Linear
Expand Down
Loading