名称 最后提交 最后更新
..
convert Support trt engine auto build in runtime for dynamic shape (#52162)
plugin [Paddle-TRT]fix bilinear_interp_v2 && some other bugs in trt 7011 (#52753)
CMakeLists.txt General Plugin Mechanism (#45355)
dynamic_shape_infermeta.cc [Hackathon NO.74] 为 Paddle-TRT 添加 grid_sampler 算子 (#50934)
dynamic_shape_infermeta_factory.h General Plugin Mechanism (#45355)
dynamic_shape_infermeta_registry.h Add symbolic shape deduction function for unfold, scatter_nd_add, p_norm, grid_sampler, pad3d, etc (#46291)
engine.cc [Paddle-Trt] Replace fc mul matmul matmul_v2 with matrix_multiply (#52222)
engine.h Cherry pick getitem/setitem 0d (#53125)
helper.h Support trt engine auto build in runtime for dynamic shape (#52162)
op_teller.cc [Paddle-Trt] Replace fc mul matmul matmul_v2 with matrix_multiply (#52222)
op_teller.h General Plugin Mechanism (#45355)
plugin_arg_mapping_context.cc [PHI]Change feed_op to phi kernel (#49116)
plugin_arg_mapping_context.h [PHI]Change feed_op to phi kernel (#49116)
test_arg_mapping_context.cc [PHI]Change feed_op to phi kernel (#49116)
test_dynamic_engine.cc Support trt engine auto build in runtime for dynamic shape (#52162)
test_engine.cc Fix bug of zero_allocator in HostAlloc (#48108)
test_tensorrt.cc trt memory set change from setMaxWorkspaceSize to setMemoryPoolLimit since trt 8.3+ (#47795)
trt_int8_calibrator.cc FIX_LINUX_Wternimate (#52307)
trt_int8_calibrator.h Remove the declaration of using Tensor in framework/tensor.h (#46432)

项目简介

PArallel Distributed Deep LEarning: Machine Learning Framework from Industrial Practice (『飞桨』核心框架,深度学习&机器学习高性能单机、分布式训练和跨平台部署)

:rocket: Github 镜像仓库 :rocket:

源项目地址 :arrow_down: :arrow_down: :arrow_down:

https://github.com/paddlepaddle/paddle

deep-learningdistributed-trainingefficiencymachine-learningneural-networkpaddlepaddlepythonscalability

发行版本 60

PaddlePaddle 2.5.0 Release Note

全部发行版

贡献者 246

全部贡献者

开发语言

  • C++ 49.8 %
  • Python 41.0 %
  • Cuda 7.0 %
  • CMake 1.1 %
  • Shell 0.6 %
反馈
建议
客服 返回
顶部