[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:
Hubert Lu
2026-01-13 17:36:01 -08:00
committed by GitHub
co-authored by wufann
parent cf25852a1d
commit afe285f7bd
7 changed files with 260 additions and 81 deletions
@@ -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