A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 07:15 UTC
[Misc] Add missing `_Backend` enums (#19081)
Signed-off-by: nicklucche <nlucches@redhat.com>
Nicolò Lucchesi committed
Jun 3, 2025 at 18:15 UTC
4b7817c119e27ad9b1e1930a34006eff9680a457
1 file changed
+2
vllm/platforms/interface.py
+2
@@ -47,6 +47,8 @@ class _Backend(enum.Enum):
47
TORCH_SDPA = enum.auto()
48
FLASHINFER = enum.auto()
49
TRITON_MLA = enum.auto() # Supported by V1
50
+ TRITON_MLA_VLLM_V1 = enum.auto()
51
+ FLASHMLA_VLLM_V1 = enum.auto()
52
FLASHMLA = enum.auto() # Supported by V1
53
HPU_ATTN = enum.auto()
54
PALLAS = enum.auto()