- 05 1月, 2022 1 次提交
-
-
由 crystal 提交于
* add elementwise div * move mul and div grad functor * Combine multiple CUDA kernels * Update the reduce interface call * add multi-output * add multi-output div * add branch judge * Package branch * Combine the x and y functions into one
-
- 04 1月, 2022 7 次提交
-
-
由 niuliling123 提交于
Add OpFunctor and replace cast, scale, clip, bce_loss and abs_grad with elementwise_no_broadcast (#38500)
-
由 Qi Li 提交于
-
由 Aurelius84 提交于
* Fix memcpyD2H sync behavior with other stream * add wait * add wait * add wait
-
由 YuanRisheng 提交于
* change 'math' to 'math_kernel' * fix compile bugs * merge develop * fix compile bugs * move cpu_impl of elementwise kernel to new directory
-
由 furnace 提交于
[NPU] add pad and pad_grad
-
由 jakpiase 提交于
-
由 Chen Weihang 提交于
* move inner cast api to cast_kernel.h * resolve conflit
-
- 31 12月, 2021 9 次提交
-
-
由 Zhangjingyu06 提交于
* [XPU]add split op for kunlun2,*test=kunlun * [XPU]add split op for kunlun2,*test=kunlun * [XPU]add split op for kunlun,*test=kunlun Co-authored-by: NQingshuChen <chenqingshu@baidu.com> -
由 JYChen 提交于
* add new api/op kthvalue * kthvalue cuda kernel to cub sorting * fix example code error * throw errors instead of LOG in cuda sort * throw errors by Paddle_ENFORCE
-
由 YuanRisheng 提交于
* change 'math' to 'math_kernel' * fix compile bugs * merge develop * fix compile bugs * fix compile bugs
-
由 zhiboniu 提交于
-
由 xiaoting 提交于
* add fold opereators, test=develop * add fold opereators, test=develop * add fold opereators, test=develop * update fold op error test, test=develop * fix unitext, test=develop * fix unitext, test=develop
-
由 Huihuang Zheng 提交于
Paddle new APIs: put_along_axis. Xu Huang is on holiday so we created this PR to work on it. It is based on his PR: https://github.com/PaddlePaddle/Paddle/pull/37921
-
由 zhiboniu 提交于
-
由 Chen Weihang 提交于
* unify data layout * fix test_transfer_layout error
-
由 YuanRisheng 提交于
* change 'math' to 'math_kernel' * fix compile bugs * merge develop * fix compile bugs
-
- 30 12月, 2021 13 次提交
-
-
由 zhiboniu 提交于
LGTM
-
由 houj04 提交于
* add sigmoid cross entropy with logits to kl1. test=kunlun * add sigmoid cross entropy with logits to kl1. test=kunlun
-
由 zhangyk0314 提交于
Add exp, abs_grad, reciprocal, reciprocal_grad operator for XPU and update xpu2_op_list.h,test=kunlun (#38570)
-
由 JYChen 提交于
* add new OP mode * rename trans-variable name and fix UT
-
由 Haohongxiang 提交于
* add cpu kernel of lstsq * update * modify code style * modify unittest * remove support for complex
-
由 zhangkaihuo 提交于
将cuSparse的handle与DeviceContext进行绑定，避免op中进行创建和销毁 添加对cuSparse中dense和sparse转换的API进行封装 添加对封装的API的单测 -
由 wenbin 提交于
* dynamic shape clone supported
-
由 limingshu 提交于
-
由 xiongkun 提交于
* refine run_program_op_grad output var name * add default for global_block. for pass the eagle_generator_cmd * fix * ; * fix * const cast * mutable block
-
由 jakpiase 提交于
* working test for padding only * added full conv2d grad kernel * removed some trash * minor change * Ci fix * format fix
-
由 Chen Weihang 提交于
* remove offset in storage * revert api change * fix custom op slice bug * fix mutable_data error
-
由 Xiaoxu Chen 提交于
* add dirichlet sample op and cpu backend kernel * add Dirichlet op cuda kernel (#6) * add dirichlet op hip kernel Co-authored-by: NFeiyu Chan <chenfeiyu@baidu.com> -
由 Leo Guo 提交于
* Fix the bug of batch_norm and batch_norm_grad op. Add the "roi_align" and "roi_align_grad" op in xpu2 op list. * Fix the bug of batch_norm and batch_norm_grad op. Add the "roi_align" and "roi_align_grad" op in xpu2 op list. test=kunlun Co-authored-by: NZibin <guozibin@baidu.com>
-
- 29 12月, 2021 5 次提交
- 28 12月, 2021 5 次提交
-
-
由 limingshu 提交于
* first commit * pass ctest of elementwise_div_grad
-
由 zyfncg 提交于
* refactor matmul directory in pten * fix merge conflict
-
由 huangxu96 提交于
* add API and op for take_along_axis * fix compile dependency problem and add example code and doc * add unitest * delete some code for CI coverage * fix code style problem * fix as review
-
由 Guoxia Wang 提交于
-
由 Tao Luo 提交于
* add amax/amin * support axis is list
-