19 lines
664 B
Python
19 lines
664 B
Python
# -*- coding: utf-8 -*-
|
||
"""iAOP-Core · 推理后端抽象层（Inference Backend）。
|
||
|
||
对应 PRD 5.6「⑥ 部署底座」与 EPIC #8：
|
||
NVIDIA GPU（5090，Triton/ONNX）与华为昇腾 NPU（ACL/CANN）实现同一
|
||
`InferenceBackend` 接口，业务代码仅依赖接口、不感知硬件；
|
||
切换后端 = 改适配层配置（`backend: gpu|npu`），业务代码零改动。
|
||
"""
|
||
from inference_backend.base import InferRequest, InferResult, InferenceBackend
|
||
from inference_backend.factory import build_backend, load_backend_config
|
||
|
||
__all__ = [
|
||
"InferenceBackend",
|
||
"InferRequest",
|
||
"InferResult",
|
||
"build_backend",
|
||
"load_backend_config",
|
||
]
|