[Attention] MLA decode optimizations (#12528)
Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com> Signed-off-by: simon-mo <xmo@berkeley.edu> Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu> Co-authored-by: simon-mo <simon.mo@hey.com> Co-authored-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Zhuohan Li <zhuohan123@gmail.com> Co-authored-by: Tyler Michael Smith <tysmith@redhat.com> Co-authored-by: Alexander Matveev <59768536+alexm-neuralmagic@users.noreply.github.com> Co-authored-by: simon-mo <xmo@berkeley.edu>
This commit is contained in:
co-authored by
Woosuk Kwon
simon-mo
Michael Goin
Zhuohan Li
Tyler Michael Smith
Alexander Matveev
simon-mo
parent
a1fc18c030
commit
cabaf4eff3
@@ -30,6 +30,7 @@ class _Backend(enum.Enum):
|
||||
TORCH_SDPA = enum.auto()
|
||||
OPENVINO = enum.auto()
|
||||
FLASHINFER = enum.auto()
|
||||
TRITON_MLA = enum.auto()
|
||||
HPU_ATTN = enum.auto()
|
||||
PALLAS = enum.auto()
|
||||
IPEX = enum.auto()
|
||||
@@ -139,7 +140,8 @@ class Platform:
|
||||
@classmethod
|
||||
def get_attn_backend_cls(cls, selected_backend: _Backend, head_size: int,
|
||||
dtype: torch.dtype, kv_cache_dtype: Optional[str],
|
||||
block_size: int, use_v1: bool) -> str:
|
||||
block_size: int, use_v1: bool,
|
||||
use_mla: bool) -> str:
|
||||
"""Get the attention backend class of a device."""
|
||||
return ""
|
||||
|
||||
|
||||
Reference in New Issue
Block a user