- 22 4月, 2022 6 次提交
-
-
由 Ming-Xu Huang 提交于
* Fix leading dimension setting error in fused_gemm_epilogue_grad_op. * Add dyload to cuBlasLt functions. * Added cublasLtMatmulAlgoGetHeuristic to improve performance. * Added FLAGS_cublaslt_exhaustive_search_times to cublasLt epilogue * Added UTs to FLAGS_cublaslt_exhaustive_search_times * Added warmup runs in algo searching of Gemm epilogue. * Update copyright and documents. * Fixed error handling.
-
由 chenjian 提交于
-
由 zhangkaihuo 提交于
-
由 Weilong Wu 提交于
* [Eager] Fix CastPyArg2Scalar in Long case * Add more test cases for paddle.clip * Use PyLong_AsLongLong
-
由 niuliling123 提交于
-
由 YuanRisheng 提交于
* Support double grad check of op in Eager mode * fix bugs of backward yaml * adjust code format
-
- 21 4月, 2022 10 次提交
-
-
由 Aganlengzi 提交于
-
由 qipengh 提交于
-
由 RichardWooSJTU 提交于
* fix nms op doc missing default value
-
由 Asthestarsfalll 提交于
* Hackathon 23 * fix bug * fix pylint error * try * fix CI-Coverage * update and add more unittest * update
-
由 jakpiase 提交于
-
由 0x45f 提交于
-
由 sneaxiy 提交于
* support int16 argmax kernel * add fp16 test
-
由 Weilong Wu 提交于
-
由 pangyoki 提交于
* add _grad_name and _grad_value for eager tensor * fix paddle_enforce * fix paddle_enforce 2 * fix grad_name * _grad_value return lodtensor rather than tensor * fix
-
由 David Nicolas 提交于
-
- 20 4月, 2022 6 次提交
-
-
由 Weilong Wu 提交于
-
由 lilong12 提交于
-
由 BrilliantYuKaimin 提交于
* 增加logspace的算子描述 * 增加logspace的形状推断 * 增加logspace核函数实现 * 在python中增加logspace接口 * 增加logspace单测 * 增加logspace * Update logspace_kernel.cu * Update logspace_op.cc * 调整代码格式 * Update doc of logspace * Update tensor.py * Update logspace_op.cc * Update logspace_kernel.cc * Update logspace_kernel.cu * Update test_logspace.py * 调整 logspace 的位置 * 调整代码格式
-
由 Yilingyelu 提交于
* gradients; test=document_fix * fix VarType; test=document_fix * fix vartype; test=document_fix * cumsum; test=document_fix * t; test=document_fix
-
由 fwenguang 提交于
-
由 Chen Weihang 提交于
* fix custom op pinned input error * fix compile error
-
- 19 4月, 2022 18 次提交
-
-
由 Chen Weihang 提交于
-
由 wangguanqun 提交于
* double accessor and show_scale * double accessor and show_scale * rename * fix bug in pslib config * add unittest
-
由 chenjian 提交于
* reduce performance influence * add unit test * fix
-
由 jakpiase 提交于
* changes for md in tensor * ci fix * Temporarily limited dims for test * ci fix * removed unnecessary includes * added reviewers suggestions * checkouted two files to avoid changing more than 19 in single PR * minor fix * reverted one file to reduce files changed to 19
-
由 chenjian 提交于
* fix according to suggestion * add kernel summary * improve coverage
-
由 Xiaoxu Chen 提交于
-
由 kuizhiqing 提交于
-
由 Jiabin Yang 提交于
* make fast through to linear * make fast through to linear * add to do for later upgrades * support build once for now
-
由 Zhang Ting 提交于
-
由 z8hanghuan 提交于
-
由 guguguzi 提交于
* fix bug for MultiplicativeDecay * remove changes to test_lr_scheduler.py
-
由 Aurelius84 提交于
* [Eager]Fix full_like/clip with np.generic type as attribute * support numpy genertic * remove usless code
-
由 qipengh 提交于
-
由 littletomatodonkey 提交于
* fix pad3d infer shape
-
由 fwenguang 提交于
-
由 zhaoyingli 提交于
* add dist reshape impl_idx=2 * fix cmakelist
-
由 Aurelius84 提交于
* [Phi]Fix expand_sig infershape BUG under static graph mode * [Phi]Fix expand_sig infershape BUG under static graph mode * [Phi]Fix unittest * [Phi]Fix unittest
-
由 ShenLiang 提交于
* fix utest * fix time
-