- 19 2月, 2021 3 次提交
-
-
由 ShenLiang 提交于
-
由 Kaipeng Deng 提交于
* fix dataloader collate return list mix tensor and numpy array. test=develop
-
由 Guanghua Yu 提交于
* add parameter in roi_align op
-
- 18 2月, 2021 5 次提交
-
-
由 Pei Yang 提交于
-
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
-
由 Huihuang Zheng 提交于
Refine fake_interface Error Message
-
由 Huihuang Zheng 提交于
Dy2stat didn't support tuple as iteration variable in the past. This PR added there main cases: 1). Non-enumerate case: for var1, var2 in var|var.numpy() will be re-written as: for FOR_ITER_TUPLE_PREFIX_x in var | var.numpy(): var1 = FOR_ITER_TUPLE_PREFIX_x[0] var2 = FOR_ITER_TUPLE_PREFIX_x[1] 2). Enumerate out tuple case: for t in enumerate(var|var.numpy) will be rewritten as: for FOR_ITER_TUPLE_INDEX_PREFIX_x, FOR_ITER_TUPLE_PREFIX_x in enumerate(var|var.numpy): t = (FOR_ITER_TUPLE_INDEX_PREFIX_x, FOR_ITER_TUPLE_PREFIX_x) 3). Enumerate inner tuple case: for i, (var1, (var2, va3)) in enumerate(var|var.numpy()) will be re-written as: for i, FOR_ITER_TUPLE_PREFIX_x in var | var.numpy(): var1 = FOR_ITER_TUPLE_PREFIX_x[0] var2 = FOR_ITER_TUPLE_PREFIX_x[1][0] var3 = FOR_ITER_TUPLE_PREFIX_x[1][1] -
由 Wojciech Uss 提交于
-
- 10 2月, 2021 1 次提交
-
-
由 WeiXin 提交于
-
- 09 2月, 2021 1 次提交
-
-
由 Chen Weihang 提交于
-
- 08 2月, 2021 2 次提交
- 06 2月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 05 2月, 2021 1 次提交
-
-
由 liuyuhui 提交于
-
- 04 2月, 2021 1 次提交
-
-
由 Jacek Czaja 提交于
-
- 03 2月, 2021 7 次提交
-
-
由 cucuzg 提交于
-
由 wawltor 提交于
fix the broadcast for the large second input
-
由 JamesLim 提交于
-
由 AshburnLee 提交于
-
由 joejiong 提交于
As the title
-
由 Adam Osewski 提交于
-
由 WangXi 提交于
-
- 02 2月, 2021 1 次提交
-
-
由 Shang Zhizhou 提交于
* fix trt plugin clone and initialize bugs * fix unit test error * enable trt in ci py3 * update unittest timeout
-
- 01 2月, 2021 3 次提交
-
-
由 Shang Zhizhou 提交于
-
由 xiemoyuan 提交于
* Add cache for Transformer encoder. * Bug fixed. * add unittests for transformer encoder.
-
由 WangXi 提交于
-
- 28 1月, 2021 2 次提交
-
-
由 Wojciech Uss 提交于
-
由 WeiXin 提交于
-
- 27 1月, 2021 3 次提交
-
-
由 liu zhengxi 提交于
* upgrade gather_tree to core.ops * update gather_tree unittests
-
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
-
由 liym27 提交于
-
- 26 1月, 2021 3 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
-
由 Leo Chen 提交于
* polish printing dtype * fix special case
- 25 1月, 2021 2 次提交
-
-
由 WangXi 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
-
- 21 1月, 2021 2 次提交
- 20 1月, 2021 1 次提交
-
-
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
-