- 24 6月, 2021 2 次提交
-
-
由 zlsh80826 提交于
* add trt LT version helper * remove deprecated nvinfer1::DimsCHW and replace it to nvinfer1::Dims3 * remove deprecated nvinfer1::DimsNCHW and replace it to nvinfer1::Dims4 * update deserialize engine * update to createNetworkV2 * update to createNetworkV2 * update buildWithConfig and remove redundent config settings * replace createNetwork to createNetworkV2 * fix int8 * addMatrixMultiply * remove unnecessary const cast * IBuilder->setInt8Calibrator() is deprecated * auto enable fp16 when using int8 * remove the redundant line
-
由 CtfGo 提交于
As the title
-
- 23 6月, 2021 13 次提交
-
-
由 feng_shuai 提交于
* tmp * pass con_element_add2_act * recover unittests CMakeLists * init pass enhance * fix the attr according to review * repair the attr conv2d * repair axis of elementwise_add * CI-coverage test=allcase * repari some attr * recover batch_norm_act * conv_elementwise_add2_act_fuse
-
由 jakpiase 提交于
* base changes for split op * 90% of split functionality added * full fp32 functionality * added bf16 test * added submemory caching * added bf test to static mode whitelist * minor change * enabled split op for inference * minor fix * minor fix
-
由 wanghuancoder 提交于
* optimize attr default value, test=develop * refine, test=develop * refine, test=develop * refine, test=develop * fix bug in AttrReader, test=develop * fix bug, test=develop * fix double_grad, test=develop * refine, test=develop * refine, test=develop * fix checker null, test=develop * for test, test=develop * refine, test=develop * refine, test=develop * refine, test=develop * refine, test=develop * refine, test=develop * refine, test=develop
-
由 Baibaifan 提交于
-
由 Wangzheee 提交于
-
由 Baibaifan 提交于
-
由 Zhanlue Yang 提交于
-
由 王明冬 提交于
-
由 王明冬 提交于
-
由 limingshu 提交于
-
由 石晓伟 提交于
-
由 wanghuancoder 提交于
* fix bug about deallocating None, test=develop
-
由 Wilber 提交于
-
- 22 6月, 2021 7 次提交
-
-
由 zhangbo9674 提交于
* new api diagonal, test=develop * add new api diagonal, test=develop * new api diagonal, test=develop * add new api paddle.diagonal, test=develop * use framework::stride replace ComputeDimStride * replace cudaMalloc/cudaMemcpy by TensorFormVector in cudaKernel and cudaGradKernel * perfect funciton: when attr(offset) is exceed attr(axis1) or attr(axis2), set the diagonal dim is 0 * fix RP-Mac-CI bug: replace framework::stride() by ComputDimStride. * perfect code-block * perfect code of python API diagonal * api supports dtype of float16 and bool * api supports dtype of float16 and bool * modify unittest code * modify unittest code * perfect dtype describe * perfect code-block
-
由 danleifeng 提交于
-
由 zhiboniu 提交于
-
由 Ren Wei (任卫) 提交于
* using argparse to handle selections * 2 TODOs * 先不更改pipeline配置，这里强制改成GPU版本 * sorted the all_names * exec gpu sample codes tests incrementally * get all apis from the pr.spec file * condition with WITH_GPU WITH_GPU == ON save * delete the useless codes * delete the useless codes. test=document_fix * echo the diff result test=document_fix * dont reuse the variables * rename fun to _func not work. put it into the skiplist https://github.com/PaddlePaddle/Paddle/commit/038ffc795025170e8cda74bcd473b46301b9a1c0 test=document_fix * skip it in check api approvals test=document_fix save * skip the private _variables * print signatures wrong. now rename it to _func test=document_fix
-
由 niuliling123 提交于
-
由 feng_shuai 提交于
-
由 TeslaZhao 提交于
-
- 21 6月, 2021 8 次提交
-
-
由 Pei Yang 提交于
-
由 lidanqing 提交于
* Add oneDNN AXPY handler. * Add fallback for small tensors. * Fix ifdefs * Remove unnecessary namespace prefixes and add missing headers. * Guard handler_axpy with proper ifdefs. * Compilation of this function is possible only when Paddle is not build with CUDA nor HIP. * Move AXPY handler code to separate files. * Use oneDNN AXPY handler in SGD op. * Use axpy handler only when Paddle is built with oneDNN. * Add test for SUM BF16 with big rows. * Fix SFINAE rules for elementwise_add_to. * Add test case for SGD with big rows. * update * update Co-authored-by: NAdam Osewski <adam.osewski@intel.com> -
由 Yuang Liu 提交于
-
由 pangyoki 提交于
* use BatchMatMul * replace TensorCopy with ShareDataWith * remove check fp16 grad * fix format * add grad_check * fix grad check
-
由 cc 提交于
* Combine amp and qat * add unit test
-
由 zhangchunle 提交于
-
由 Leo Chen 提交于
* enable npu alignment * support flatten_params/grads * support clip by global norm * remove memset in coalesce_tensor_op * fix npu kernel of sum op when input is one tensor * add ut for flatten_param_grads+regularizer * fix ut * fix typo
-
由 李季 提交于
-
- 18 6月, 2021 6 次提交
- 17 6月, 2021 4 次提交
-
-
由 王明冬 提交于
-
由 Wilber 提交于
-
由 wanghuancoder 提交于
-
由 Wilber 提交于
[Inference Tensorrt] Add attr for trt engine and handle the input seq problem for ernie var len. (#33575)
-