Skip to content

Move tokamax_group_sizes calculation inside tokamax branch. #3715

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
copybara-service wants to merge 1 commit into
base: main
Choose a base branch
from
+3 −1
Open

Move tokamax_group_sizes calculation inside tokamax branch. #3715

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
4 changes: 3 additions & 1 deletion src/maxtext/layers/moe.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1043,7 +1043,6 @@ def gmm(inputs, kernel, tiling, group_sizes, expert_assignments, weight_gather_a
if inputs.shape[0] != expert_assignments.shape[0]:
raise ValueError("The number of input tokens must match the number of expert assignments!")

tokamax_group_sizes = get_tokamax_group_sizes(group_sizes, inputs, kernel)
orig_inputs_shape = inputs.shape # save shape of inputs before potentially padding.
inputs, padding_amount = max_utils.maybe_pad(inputs, self.config.wi_tile_fwd_batch_seq)
inputs = inputs.astype(self.dtype)
Expand All @@ -1067,6 +1066,9 @@ def gmm(inputs, kernel, tiling, group_sizes, expert_assignments, weight_gather_a
weight_gather_axes=weight_gather_axes,
)
else: # tokamax (unquantized)
tokamax_group_sizes = get_tokamax_group_sizes(
group_sizes, inputs, kernel
)
output = tokamax.ragged_dot(
lhs=inputs,
rhs=kernel,
Expand Down
Loading