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, 22:00 UTC
[Bugfix] Fix OpenVINOExecutor abstractmethod error (#6296)
Signed-off-by: sangjune.park <sangjune.park@navercorp.com>
sangjune.park committed
Jul 11, 2024 at 02:03 UTC
44cc76610d0b23ce5d609867f6dae7e033dee818
1 file changed
+16
vllm/executor/openvino_executor.py
+16
@@ -90,6 +90,22 @@ class OpenVINOExecutor(ExecutorBase):
90
def list_loras(self) -> Set[int]:
91
return self.driver_worker.list_loras()
92
93
+ def add_prompt_adapter(self, prompt_adapter_request) -> bool:
94
+ raise NotImplementedError(
95
+ "Soft prompt is currently not supported by the OPENVINO backend.")
96
+
97
+ def remove_prompt_adapter(self, prompt_adapter_id: int) -> bool:
98
+ raise NotImplementedError(
99
+ "Soft prompt is currently not supported by the OPENVINO backend.")
100
+
101
+ def pin_prompt_adapter(self, prompt_adapter_id: int) -> bool:
102
+ raise NotImplementedError(
103
+ "Soft prompt is currently not supported by the OPENVINO backend.")
104
+
105
+ def list_prompt_adapters(self) -> Set[int]:
106
+ raise NotImplementedError(
107
+ "Soft prompt is currently not supported by the OPENVINO backend.")
108
+
109
def check_health(self) -> None:
110
# OpenVINOExecutor will always be healthy as long as
111
# it's running.