Skip to content

DLRMv4: compute the last HSTU layer only for the rows the loss reads - #903

Open
jiaweche wants to merge 1 commit into
mlcommons:masterfrom
jiaweche:targets-only
Open

jiaweche wants to merge 1 commit into
mlcommons:masterfrom
jiaweche:targets-only

[DLRMv4] Shrink the last HSTU layer to the rows the loss reads

e60300b
Select commit
Loading
Failed to load commit list.
Sign in for the full log view

Annotations

1 warning
checklist
succeeded Aug 28, 2026 in 8s