Skip to content

config change to enable pre compute scale for fp8 #2536

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

config change to enable pre compute scale for fp8 #2536

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
3 changes: 3 additions & 0 deletions torchao/float8/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -183,6 +183,9 @@ class Float8LinearConfig:
# implements pre/post-all-gather methods to do float8 all-gather with FSDP2.
enable_fsdp_float8_all_gather: bool = False

# If True, then pre compute the scale of the weights in fp8 linear module
pre_compute_fp8_all_gather_weights_scale: bool = False

# If True, then prior to performing the fp8 scaled mamtmul we will pad the
# inner dimension of a (dim 1) and b (dim 2) with 0s. This is needed for matmuls
# _scaled_mm since it has the strong constraint that for M,N,K N, K must be a multiple of 16.
Expand Down
Loading