Skip to content

Reuse forward histograms in Triton TBE backward (#4491) #4491

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

Closed
stashuk-olek wants to merge 8 commits into from
Closed

Reuse forward histograms in Triton TBE backward (#4491) #4491

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
1c94984
Select CUDA v2 bounds checking for Triton TBE (#4484)
stashuk-olek Aug 8, 2026
fe73e5d
Fuse Triton TBE forward bounds checking (#4485)
stashuk-olek Aug 8, 2026
4b6e401
Optimize Triton TBE forward for small long-bag tables (#4486)
stashuk-olek Aug 8, 2026
2006579
Reduce Triton TBE backward reduction pressure (#4487)
stashuk-olek Aug 8, 2026
6483b7a
Reduce Triton TBE unweighted backward reduction width (#4488)
stashuk-olek Aug 8, 2026
f0e4a2b
Coarsen Triton TBE forward bag scheduling (#4489)
stashuk-olek Aug 8, 2026
703262c
Widen Triton TBE forward gather issue (#4490)
stashuk-olek Aug 8, 2026
aa5c4b8
Reuse forward histograms in Triton TBE backward (#4491)
stashuk-olek Aug 8, 2026
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
2 changes: 2 additions & 0 deletions torchrec/distributed/batched_embedding_kernel.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3894,6 +3894,7 @@ def __init__(
)
output_dtype = output_dtype_sparse.as_dtype()
stochastic_rounding = fused_params.get("stochastic_rounding", True)
bag_size_hints: Optional[List[int]] = fused_params.get("bag_size_hints")

# Create Triton TBE module with feature_table_map for correct batch size handling
self._emb_module: TritonTableBatchedEmbeddingBags = (
Expand All @@ -3907,6 +3908,7 @@ def __init__(
eps=eps,
optimizer=optimizer,
device=device,
bag_size_hints=bag_size_hints,
)
)

Expand Down
Loading
Loading