12 Commits

Author	SHA1	Message	Date
Wang Xinyu	caa369f64a	[Backend] TRT cast GPU input from int64 to int32, output from int32 to int64, and Windows support building CUDA files (#426) ... * TRT cast int64 to int32 * windows cmake build cuda src * fix windows cmake error when build cuda src * add a notice in windows gpu build doc * cmake add cuda std=11 * TRT cast output from int32 to int64 * nits * trt get original input output dtype	2022-10-28 13:38:06 +08:00
heliqi	b064ddf7ed	[Serving][backend]serving support multi stream and backend support external stream (#431) ... * serving support multi stream * pybind add external stream Co-authored-by: Jason <jiangjiajun@baidu.com>	2022-10-26 14:46:13 +08:00
Wang Xinyu	43d86114d8	[Backend] TRT backend & PP-Infer backend support pinned memory (#403) ... * TRT backend use pinned memory * refine fd tensor pinned memory logic * TRT enable pinned memory configurable * paddle inference support pinned memory * pinned memory pybindings Co-authored-by: Jason <jiangjiajun@baidu.com>	2022-10-21 18:51:36 +08:00
yeliang2258	2a68a23baf	Add paddle quantize model support for ORT, TRT and MKLDNN deploy backend (#257) ... * add quantize model support for trt and paddle * fix bugs * fix * update paddle2onnx version * update version * add quantize test Co-authored-by: Jason <jiangjiajun@baidu.com>	2022-10-09 20:00:05 +08:00
heliqi	0805ead0ed	add 'GetOutputInfos' and 'GetInputInfos' interface (#232) ... add GetOutputInfos GetInputInfos	2022-09-15 13:09:31 +08:00
Jason	68523be411	Modify file structure to separate python and cpp code (#223) ... Modify code structure	2022-09-14 15:44:13 +08:00
Jason	ffbc5cc42d	Move cpp code to directory csrcs (#42) ... * move cpp code to csrcs * move cpp code to csrcs	2022-07-26 17:59:02 +08:00
Jason	17e4dc6b5e	Support remove multiclass_nms to enable ppyoloe to tensorrt (#40) ... * Add custom operator for onnxruntime ans fix paddle backend * Polish cmake files and runtime apis * Remove copy libraries * fix some issue * fix bug * fix bug * Support remove multiclass_nms to enable paddledetection run tensorrt * Support remove multiclass_nms to enable paddledetection run tensorrt * Support remove multiclass_nms to enable paddledetection run tensorrt * Support remove multiclass_nms to enable paddledetection run tensorrt * add common operator multiclassnms * fix compile problem Co-authored-by: root <root@bjyz-sys-gpu-kongming3.bjyz.baidu.com>	2022-07-26 11:16:01 +08:00
Jason	279c993483	Polish cmake files and runtime apis (#36) ... * Add custom operator for onnxruntime ans fix paddle backend * Polish cmake files and runtime apis * Remove copy libraries * fix some issue * fix bug * fix bug	2022-07-25 08:59:53 +08:00
Jason	90061e11f5	Fix outputs order of tensorrt (#18) ... * fix trt output order * Update trt_backend.cc	2022-07-14 19:19:56 +08:00
DefTruth	a45f189b56	fixed missing trt_backend option & remove un-need data layout check in Cast (#14) ... * update .gitignore * Added checking for cmake include dir * fixed missing trt_backend option bug when init from trt * remove un-need data layout and add pre-check for dtype * changed RGB2BRG to BGR2RGB in ppcls model * Update CMakeLists.txt	2022-07-12 15:14:30 +08:00
jiangjiajun	9d87046d78	first commit	2022-07-05 09:30:15 +00:00