[Kernel] Flashinfer MLA (trtllm-gen) decode kernel integration (#21078)

Signed-off-by: hjjq <hanjieq@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
This commit is contained in:
Hanjie Qiu
2025-09-10 15:31:10 -07:00
committed by GitHub
co-authored by Michael Goin
parent fba7856581
commit dcb28a332b
8 changed files with 255 additions and 1 deletions
+1
View File
@@ -51,6 +51,7 @@ class _Backend(enum.Enum):
TORCH_SDPA_VLLM_V1 = enum.auto()
FLASHINFER = enum.auto()
FLASHINFER_VLLM_V1 = enum.auto()
FLASHINFER_MLA = enum.auto()
TRITON_MLA = enum.auto() # Supported by V1
TRITON_MLA_VLLM_V1 = enum.auto()
CUTLASS_MLA = enum.auto()