- 24 8月, 2022 2 次提交
- 23 8月, 2022 14 次提交
-
-
由 pangyoki 提交于
-
由 zhaoyingli 提交于
* add quant pass
-
由 LiYuRio 提交于
-
由 Sing_chan 提交于
-
由 niuliling123 提交于
-
由 zhangkaihuo 提交于
* rename the member function of SparseTensor * use shorter function names
-
由 limingshu 提交于
-
由 OccupyMars2025 提交于
-
由 Siming Dai 提交于
-
由 thunder95 提交于
* erfinv * fix some tiny issues
-
由 LiYuRio 提交于
-
由 OccupyMars2025 提交于
* Update scope.h * typo * Update dense_tensor.inl
-
由 YuanRisheng 提交于
* move distribute_fpn_proposals * fix some code * fix yaml bugs * add set dtype * move proposal_impl to funcs * fix compile bugs
-
由 ronnywang 提交于
* [CustomDevice] add profiler apis * migrate CalculateEstOccupancy into cuda_tracer * update * add ut
-
- 22 8月, 2022 9 次提交
-
-
由 joanna.wozna.intel 提交于
* Add int8 support for matmul+elementwiae_add fuse * Corrections after review and ernie test fix
-
由 Sławomir Siwek 提交于
* merge conv_concat_relu to conv_act * fix typo * extend unit test * reuse existing gpd * codestyle * enforce mkldnn conv
-
由 zhoutianzi666 提交于
-
由 wanghuancoder 提交于
some python c api use final state
-
由 zhangkaihuo 提交于
-
由 shangliang Xu 提交于
-
由 Yuanle Liu 提交于
-
由 Hui Zhang 提交于
* fix jit layer function * fix comment * fix comment
-
由 ronnywang 提交于
-
- 20 8月, 2022 2 次提交
-
-
由 wanghuancoder 提交于
* pylayer detach output tensor if it is equal with input * pylayer detach output tensor if it is equal with input
-
由 Sing_chan 提交于
* add max_p without test * add test of max_p * make max_p consistent with paddle.maximum
-
- 19 8月, 2022 12 次提交
-
-
由 pangyoki 提交于
* add forward inplace final state api * fix bug * fix reshape * fix coverage * add inplace info for erfinv, lerp, put_along_axis * fix put_along_axis infer_meta * fix format * update yaml * fix
-
由 王明冬 提交于
-
由 Wang Bojun 提交于
* fix layernormTrt meanVar alloc bug
-
由 HongyuJia 提交于
-
由 Ruibiao Chen 提交于
* Fix random op depenency and lr_shedule bugs for standalone executor * Fix CI errors * Fix CI errors * Fix CI errors
-
由 Wang Bojun 提交于
* add group_norm dyanmic plugin
-
由 houj04 提交于
-
由 mengqingchun02 提交于
* support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * make up beam_search_decode operator test cases on xpu and cpu environment. test=kunlun
-
由 dongfangshenzhu 提交于
* add merged_momentum *test=kunlun * add merged_momentum *test=kunlun * add fp16 to merged_momentum,*test=kunlun * change dist_model.cc * add merged_momentum unittest and change momentum,test=kunlun * add merged_momentum unittest and change momentum,test=kunlun * add merged_momentum unittest and change momentum,test=kunlun * add merged_momentum unittest and change momentum,test=kunlun
-
由 Charles-hit 提交于
* 修复生成动态图代码时，如果输出没有配置名字，会导致下标越界的问题。 * decide forward_return[0] is not none * 修改反向yaml前向输出只有一个时，未配置名字，那么输出自动生成为out * modify code style
-
由 mengqingchun02 提交于
* support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * support beam_search operator on xpu. test=kunlun * fix beam_search operator bugs on xpu. test=kunlun * fix beam_search operator bugs on xpu. test=kunlun * fix beam_search operator bugs on xpu. test=kunlun * fix beam_search operator bugs on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun * support beam_search_decode operator on xpu. test=kunlun
-
由 Aganlengzi 提交于
-
- 18 8月, 2022 1 次提交
-
-
由 heliqi 提交于
* predictor add GetInputType interface * predictor change GetInputType to GetInputTypes * predictor add tester * predictor add tester * predictor change GetInputType to GetInputTypes * predictor change GetInputType to GetInputTypes * predictor add tester
-