Skip to content

Add batch_number to AbstractInputBatch. #58

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

Merged
copybara-service merged 1 commit into from
Jul 16, 2025
Merged

Add batch_number to AbstractInputBatch. #58

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: 4 additions & 0 deletions recml/layers/linen/sparsecore.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,10 +276,12 @@ class SparsecorePreprocessor:
sparsecore_config: The sparsecore config used to create the tables.
global_batch_size: The global batch size across all devices to partition the
inputs across.
_batch_number: The batch number for preprocessing, incremented on each call.
"""

sparsecore_config: SparsecoreConfig
global_batch_size: int
_batch_number: int = dataclasses.field(init=False, default=0)

def __post_init__(self):
self.sparsecore_config.init_feature_specs(self.global_batch_size)
Expand Down Expand Up @@ -328,6 +330,7 @@ def _to_np(x: Any) -> np.ndarray:
if weights[key] is not None:
weights[key] = np.reshape(weights[key], (-1, 1))

self._batch_number += 1
csr_inputs, _ = embedding.preprocess_sparse_dense_matmul_input(
features=features,
features_weights=weights,
Expand All @@ -337,6 +340,7 @@ def _to_np(x: Any) -> np.ndarray:
num_sc_per_device=self.sparsecore_config.num_sc_per_device,
sharding_strategy=self.sparsecore_config.sharding_strategy,
allow_id_dropping=False,
batch_number=self._batch_number,
)

processed_inputs = {
Expand Down