[NVIDIA] Add Cutlass MLA backend (#17625)
This commit is contained in:
@@ -51,6 +51,7 @@ class _Backend(enum.Enum):
|
||||
TRITON_MLA_VLLM_V1 = enum.auto()
|
||||
FLASHMLA_VLLM_V1 = enum.auto()
|
||||
FLASHMLA = enum.auto() # Supported by V1
|
||||
CUTLASS_MLA_VLLM_V1 = enum.auto()
|
||||
HPU_ATTN = enum.auto()
|
||||
PALLAS = enum.auto()
|
||||
PALLAS_VLLM_V1 = enum.auto()
|
||||
|
||||
Reference in New Issue
Block a user