[AMD] enable CUDA graph for NSA backend and fix NSA FP8 fused RMSNorm group quant (#16841)
Co-authored-by: wufann <715544327@qq.com>
This commit is contained in:
@@ -174,6 +174,9 @@ class NSAIndexerMetadata(BaseIndexerMetadata):
|
||||
def get_page_table_64(self) -> torch.Tensor:
|
||||
return self.attn_metadata.real_page_table
|
||||
|
||||
def get_page_table_1(self) -> torch.Tensor:
|
||||
return self.attn_metadata.page_table_1
|
||||
|
||||
def get_seqlens_expanded(self) -> torch.Tensor:
|
||||
return self.attn_metadata.nsa_seqlens_expanded
|
||||
|
||||
|
||||
Reference in New Issue
Block a user