关于GCU、沐曦GPGPU、MLU、0卡V100资源4月7日恢复上架的公告>>> 关于共建具身智能开源数据集的倡议>>> 关于云脑任务中统一路径访问方式的公告>>> 关于将启智集群GPU资源迁移至智算集群的公告>>>

yeliang2258 cae341e6c5 [Backend] Add fp16 support for ONNXRuntime-GPU (#1239 ) * add fp16 support for ort-gpu * add enable_ort_fp16 option * fix * fix bugs * use fp16 for test * update code * update code * fix windows bug		1 year ago
.github	[Doc] Fix docs for KunlunXin, A311D and issue template (#1551)	1 year ago

benchmark	[Benchmark]Add Failed Log (#1693)	1 year ago

c_api	[C API] Add create api for c results (#1547)	1 year ago

cmake	[Backend] Add fp16 support for ONNXRuntime-GPU (#1239)	1 year ago

cpack	[Other] Generate Debian package and RPM package (#1043)	1 year ago

csharp	[Tutorial Doc] add tutorial for how to use c and c sharp api (#1392)	1 year ago

docs	[Doc] add vision processor python api doc (#1655)	1 year ago

examples	[Docs] Pick PPOCR fastdeploy docs from PaddleOCR (#1534)	1 year ago

fastdeploy	[Backend] Add fp16 support for ONNXRuntime-GPU (#1239)	1 year ago

java/android	Update README.md	1 year ago

paddle2onnx	[Build] Support build with source code of Paddle2ONNX (#1559)	1 year ago

poros	update poros README.md (#1393)	1 year ago

python	[Doc] add vision processor python api doc (#1655)	1 year ago

scripts	[Build] Support build with source code of Paddle2ONNX (#1559)	1 year ago

serving	[Serving] Add collect shape and fix serving infer (#1658)	1 year ago

streamer	[Streamer] Build without deepstream, add CPU decoder (#1178)	1 year ago

tests	[Benchmark] Add precision evaluation api from benchmark (#1310)	1 year ago

third_party	[Build] Support build with source code of Paddle2ONNX (#1559)	1 year ago

tools	[Bug Fix] fix a bug in paddle2coreml tool (#1481)	1 year ago

tutorials	[CVCUDA]add op Python API: Cast, HWC2CHW, Normalize, PadToSize, Resize, StridePad (#1589)	1 year ago

.clang-format	[Other] Seperate option from backends (#1048)	1 year ago

.clang_format.hook	first commit	1 year ago

.cpplint_pre_commit.hook	first commit	1 year ago

.gitignore	[Bug Fix] fix build error while enable flycv on linux x64 (#1365)	1 year ago

.pre-commit-config.yaml	[Other] Seperate option from backends (#1048)	1 year ago

CMakeLists.txt	[cmake] switch paddle 2.4-dev7 -> 2.4-dev6 for windows (#1660)	1 year ago

CODE_OF_CONDUCT.md	Add CODE_OF_CONDUCT.md (#573)	1 year ago

FastDeploy.cmake.in	[Build] Support build with source code of Paddle2ONNX (#1559)	1 year ago

FastDeployCSharp.cmake.in	[C# api] add c sharp api for fastdeploy (#1246)	1 year ago

LICENSE	first commit	1 year ago

README.md	Update README.md	1 year ago

README_CN.md	Update README_CN.md	1 year ago

README_EN.md	[Doc] Fix wrong word (#1380)	1 year ago

ThirdPartyNotices.txt	Update ThirdPartyNotices.txt	1 year ago

VERSION_NUMBER	Update VERSION_NUMBER	1 year ago

commit-prepare.sh	first commit	1 year ago

docs/README.md

Tutorials

简体中文| English

Tutorials

Install

A Quick Start - Demos

API

Performance Optimization

Quantization Acceleration

Frequent Q&As

More FastDeploy Deployment Module

FastDeploy是一款全场景、易用灵活、极致高效的AI推理部署工具，支持云边端部署。提供超过 160+ Text，Vision， Speech和跨模态模型开箱即用的部署体验，并实现端到端的推理性能优化。包括物体检测、字符识别（OCR）、人脸、人像扣图、多目标跟踪系统、NLP、Stable Difussion文图生成、TTS 等几十种任务场景，满足开发者多场景、多硬件、多平台的产业部署需求。

C++ Python Java Markdown Text other

54695910+leiqing1@users.noreply.github.com jiangjiajun@baidu.com 31974251+DefTruth@users.noreply.github.com imylovex1@163.com 852142024@qq.com zhoushunjie@baidu.com wjjisloser@163.com 109218879+yunyaoXYY@users.noreply.github.com 58363586+Zheng-Bicheng@users.noreply.github.com 1101791222@qq.com 67993288+ziqi-jin@users.noreply.github.com chenjian26@baidu.com 30516196+yeliang2258@users.noreply.github.com 849453582@qq.com 1558270516@qq.com wangxinyu_es@163.com 53218160+Zeref996@users.noreply.github.com

35565423+HexToString@users.noreply.github.com chenzeyu01@baidu.com 44280887+GodIsBoom@users.noreply.github.com 49013063+CoolKbh@users.noreply.github.com 115439700+charl-u@users.noreply.github.com wang_bojun@outlook.com shaywxy@gmail.com

How to access data resources in code