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 16, 05:45 UTC
[Hardware][Gaudi]add get_name method for HPUAttentionBackend (#10667)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Kunshang Ji committed
Nov 27, 2024 at 14:49 UTC
e85250b1d164c9975816fa7aaf591aa5abad577d
1 file changed
+4
vllm/attention/backends/hpu_attn.py
+4
@@ -22,6 +22,10 @@ logger = init_logger(__name__)
22
23
class HPUAttentionBackend(AttentionBackend):
24
25
+ @staticmethod
26
+ def get_name() -> str:
27
+ return "HPU_ATTN"
28
+
29
@staticmethod
30
def get_impl_cls() -> Type["HPUAttentionImpl"]:
31
return HPUAttentionImpl