[Kernel] Batch invariant NVFP4 MoE using cutlass (#40372)
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com> Co-authored-by: OpenAI Codex <codex@openai.com> Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
This commit is contained in:
co-authored by
OpenAI Codex
Wentao Ye
parent
41a7e7da0c
commit
c25093a305
@@ -734,6 +734,10 @@ class CutlassExpertsFp4(mk.FusedMoEExpertsModular):
|
||||
# needed for STANDARD activation format kernels in EP mode.
|
||||
return moe_parallel_config.ep_size == 1
|
||||
|
||||
@staticmethod
|
||||
def _supports_batch_invariance() -> bool:
|
||||
return True
|
||||
|
||||
@staticmethod
|
||||
def activation_format() -> mk.FusedMoEActivationFormat:
|
||||
return mk.FusedMoEActivationFormat.Standard
|
||||
|
||||
Reference in New Issue
Block a user