Wang Bojun 7b58387d3c add option for inference precision and cutlass (#2017) ...

* add option for inference precision and cutlass

* code clean

* code refine

* code refine

2023-06-09 10:20:48 +08:00

..

common/cuda

[Backend] Add TensorRT FP16 support for AdaptivePool2d (#1116)

2023-01-13 19:44:00 +08:00

horizon

【Hackthon_4th 180】Support HORIZON BPU Backend for FastDeploy (#1822)

2023-05-06 16:10:37 +08:00

lite

[XPU] Add docs for gm_default_size and fix type (#1962)

2023-05-18 20:30:06 +08:00

openvino

[Backend] optimize cpu usage on openvino backend (#1531)

2023-03-17 10:24:25 +08:00

ort

[Backend] Add fp16 support for ONNXRuntime-GPU (#1239)

2023-03-23 18:23:13 +08:00

paddle

add option for inference precision and cutlass (#2017)

2023-06-09 10:20:48 +08:00

poros

[Other] Optimize poros backend (#1331)

2023-02-17 14:32:35 +08:00

rknpu2

[Backend] Refactoring RKNPU2 Backend code (#1772)

2023-04-13 16:37:36 +08:00

sophgo

[Hackthon_4th 177] Support PP-YOLOE-R with BM1684 (#1809)

2023-04-21 10:48:05 +08:00

tensorrt

[Model] Add Paddle3D smoke model (#1766)

2023-04-14 16:30:56 +08:00

tvm

[Backend] Add pybind & PaddleDetection example for TVM (#1998)

2023-06-04 13:26:47 +08:00

backend.h

[Example] Update runtime examples (#1542)

2023-03-08 16:56:04 +08:00