| Remove the unsupported valid_targets in opt_base (#9814) | 3 年前 |
| Remove fluid api (#10357) | 3 年前 |
| [ARM]Add one-click profile tools (#10064) | 3 年前 |
| publish lite (#1800) | 7 年前 |
| 【DOCKER&CI】add gcc82 docker with cuda (#2758) | 6 年前 |
| Open [Framework]Update docker image script (#5830) | 5 年前 |
| 【doc and opt tool】add auto_transform.sh into Paddle-Lite project and modify related docs #2973 | 6 年前 |
| update benchmark.sh, support arm cpu fp16 && fp32 benchmark test (#9579) | 3 年前 |
| support opt tools compile in aarch64 (#9776) | 3 年前 |
| [Autoscan] add 0D-tensor test for CPU (#10214) | 3 年前 |
| 增加OPENCL 和 ARM联合裁剪脚本 test=develop | 4 年前 |
| 增加Android OpenCL裁剪脚本, 修改注释, test=develop | 5 年前 |
| 增加Android OpenCL裁剪脚本 | 5 年前 |
| [Arm] Rename adnn to arm_dnn_library (#10201) | 3 年前 |
| [doc] fix tailoring doc for ios,test=document_fix (#7112) | 4 年前 |
| [NNAdapter] Fix nnadapter google_xnnpack backend compile error (#10623) | 1 年前 |
| [Autoscan] add 0D-tensor test for CPU (#10214) | 3 年前 |
| [OHOS] Support for harmony os next (#10654) | 1 年前 |
| [Arm] Rename adnn to arm_dnn_library (#10201) | 3 年前 |
| [X86] Add set value op and double data type to framework. (#9580) * [QualcommQnn] add ops (#9538) support fusion_elementwise_mul_activation, fusion_elementwise_sub_activation, fusion_elementwise_div_activation, fusion_elementwise_min_activation, fusion_elementwise_max_activation, fusion_elementwise_pow_activation, instance_norm, prelu, arg_max, arg_min, flatten, flatten2, norm * add float64 type to lite * add float64 kernel for set value * change the third-party-libs url due to flatbuf update. * fix include files conflict * fix bug * Fix heterogeneous execution errors * fix control_flow_op_control_flow_op_shared_inputs_and_outputs_place_sync_pass bug * fix comment Co-authored-by: zhupengyang <zhu_py@qq.com> | 3 年前 |
| [Metal] Fix project build metal shader bugs (#10544) * [Metal] Fix concat error, fix fetch typo error (#10541) * [Metal] fix build_xcode.sh error, add building with metal option (#10542) | 2 年前 |
| [BUG FIX] Bug fix on python opt tool (#6033) | 5 年前 |
| update python code style (#7954) | 4 年前 |
| add symbol check script to CI.test=develop (#5700) | 5 年前 |
| [X86] Add set value op and double data type to framework. (#9580) * [QualcommQnn] add ops (#9538) support fusion_elementwise_mul_activation, fusion_elementwise_sub_activation, fusion_elementwise_div_activation, fusion_elementwise_min_activation, fusion_elementwise_max_activation, fusion_elementwise_pow_activation, instance_norm, prelu, arg_max, arg_min, flatten, flatten2, norm * add float64 type to lite * add float64 kernel for set value * change the third-party-libs url due to flatbuf update. * fix include files conflict * fix bug * Fix heterogeneous execution errors * fix control_flow_op_control_flow_op_shared_inputs_and_outputs_place_sync_pass bug * fix comment Co-authored-by: zhupengyang <zhu_py@qq.com> | 3 年前 |
| [X86] Add set value op and double data type to framework. (#9580) * [QualcommQnn] add ops (#9538) support fusion_elementwise_mul_activation, fusion_elementwise_sub_activation, fusion_elementwise_div_activation, fusion_elementwise_min_activation, fusion_elementwise_max_activation, fusion_elementwise_pow_activation, instance_norm, prelu, arg_max, arg_min, flatten, flatten2, norm * add float64 type to lite * add float64 kernel for set value * change the third-party-libs url due to flatbuf update. * fix include files conflict * fix bug * Fix heterogeneous execution errors * fix control_flow_op_control_flow_op_shared_inputs_and_outputs_place_sync_pass bug * fix comment Co-authored-by: zhupengyang <zhu_py@qq.com> | 3 年前 |
| update python code style (#7954) | 4 年前 |
| update python code style (#7954) | 4 年前 |
| Remove the deprecated implement of NVIDIA CUDA GPU. (#9616) | 3 年前 |
| [LITE][BENCHMARK] enhance android arm cpu benchmark (#1939) * enhance benchmark * update code format. test=develop | 7 年前 |
| port lite code (#1819) | 7 年前 |
| test=develop, add the untar.py for windows (#3472) test=develop, move the build.bat to lite/tools | 6 年前 |