- 23 2月, 2021 5 次提交
-
-
由 Guanghua Yu 提交于
-
由 Qi Li 提交于
-
由 wangchaochaohu 提交于
* fix windows for optimization of elementwise_add Op
-
由 joanna.wozna.intel 提交于
* Unification of bfloat16 enablement process and refactor * Remove unnecessary function * Standardize the output name search
-
由 Zhong Hui 提交于
[BUG FIX] Fix softmax cross entropy overflow problem.
-
- 22 2月, 2021 1 次提交
-
-
由 JamesLim 提交于
-
- 20 2月, 2021 2 次提交
-
-
由 TTerror 提交于
add squeeze_op/unsqueeze_op on kunlun;fix conv op and parallel executor;optimize lookup_table op (#31056) * add squeeze_op/unsqueeze_op on kunlun; fix conv op and parallel executor on kunlun; optimize lookup_table op on kunlun * update squeeze/unsqueeze op
-
由 liym27 提交于
* [static setitem] support the index step > 1. tensor_a[::3] = value * [static setitem] support the index step < 0. Eg: tensor_a[::-3] = value * [static setitem] support the index is Tensor. eg: tensor_a[tensor_3:0:-1] = value * Add op version.
-
- 19 2月, 2021 3 次提交
-
-
由 Jacek Czaja 提交于
* - added Reshape grad bf16 * - Added reshape grad bf16 * - cosmetics in py
-
由 Wojciech Uss 提交于
* Modify relu native implementation * fix GPU performance
-
由 Guanghua Yu 提交于
* add parameter in roi_align op
-
- 18 2月, 2021 2 次提交
-
-
由 Zhang Ting 提交于
* enable exhaustive_search for input_grad when dtype is float16 * enable exhaustive_search for forward algos
-
由 joanna.wozna.intel 提交于
* Add conv transpose BF16 * Share function GetWeightsTz * Adjust to review and fix op compatibility * Add bias to unique handler name * Remove errors related to paddle enforce * Add conv2d_transpose to bf16 list and kernel refator
-
- 09 2月, 2021 1 次提交
-
-
由 Chen Weihang 提交于
-
- 08 2月, 2021 1 次提交
-
-
由 liym27 提交于
-
- 06 2月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 05 2月, 2021 2 次提交
-
-
由 liuyuhui 提交于
-
由 taixiurong 提交于
-
- 04 2月, 2021 2 次提交
-
-
由 Jacek Czaja 提交于
-
由 wanghuancoder 提交于
* use iwyu clean include second time, test=develop
-
- 03 2月, 2021 6 次提交
- 02 2月, 2021 1 次提交
-
-
由 joanna.wozna.intel 提交于
-
- 01 2月, 2021 1 次提交
-
-
由 Wilber 提交于
* update lite tag * disable ut
-
- 29 1月, 2021 1 次提交
-
-
由 Zhen Wang 提交于
-
- 28 1月, 2021 2 次提交
-
-
由 Wojciech Uss 提交于
-
由 taixiurong 提交于
* transformer predict * trans bug fix
-
- 27 1月, 2021 1 次提交
-
-
由 jakpiase 提交于
* added external reorder to profiler * resolved conflict * added enable_static * initial version of lstm, not working yet * added lstm to operators.cmake * added vanilla lstm mkldnn op * added peephole weights integration * minor changes * added formatting * added fusion_lstm_mkldnn to static_whitelist * added formatting * removed comment * moved use_peepholes attribute inside is_cached block * reverted wrong changes * minor formatting change * minor changes * changed stream handling * minor change * added datatype to GetExpectedKernelType() * added reading stream from TLS
-
- 26 1月, 2021 2 次提交
-
-
由 jakpiase 提交于
* added external reorder to profiler * resolved conflict * added enable_static * initial version of lstm, not working yet * added lstm to operators.cmake * added vanilla lstm mkldnn op * added peephole weights integration * minor changes * added formatting * added fusion_lstm_mkldnn to static_whitelist * added formatting * removed comment * moved use_peepholes attribute inside is_cached block * reverted wrong changes * minor formatting change * minor changes
- 25 1月, 2021 3 次提交
-
-
由 arlesniak 提交于
* More precise mkldnn kernel choice in GetExpectedKernelType * Fixes after review * Refresh develop for CI * CI experiment * get back from CI exper
-
由 Jacek Czaja 提交于
-
由 chentianyu03 提交于
* add abs test case * use std::abs to fix abs bug * fix the abs bug * fix abs bug
-
- 22 1月, 2021 1 次提交
-
-
由 ShenLiang 提交于
-
- 20 1月, 2021 2 次提交
-
-
由 Jacek Czaja 提交于
-
由 TTerror 提交于
* support reduce_max op on kunlun * support reduce_max op on kunlun * support reduce_max op on kunlun * support reduce_max op on kunlun
-