[Kernel] Resubmit PR 48666 - Gemma4 FP8 KV FA4 head dim 512 backend selection (#53175)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
This commit is contained in:
@@ -57,7 +57,7 @@ class DeepseekV4SparseMLABackend(AttentionBackend):
|
||||
]
|
||||
|
||||
@staticmethod
|
||||
def get_supported_kernel_block_sizes() -> list[int | MultipleOf]:
|
||||
def get_supported_kernel_block_sizes(kv_cache_spec=None) -> list[int | MultipleOf]:
|
||||
return [256]
|
||||
|
||||
@staticmethod
|
||||
|
||||
Reference in New Issue
Block a user