- 14 3月, 2019 1 次提交
-
-
由 liuwei1031 提交于
2. remove lod check in reshape op test=develop
-
- 13 3月, 2019 4 次提交
-
-
由 sneaxiy 提交于
test=develop
-
由 guomingz 提交于
* resolve #15618 Backgroud: the PR #15398 raised the box_coder op performance regression, we optimized the code via the more efficency leveraging opemmp.
-
由 sneaxiy 提交于
test=develop
-
由 baojun 提交于
* remove concast_cast and refactor code test=develop * reduce flag use test=develop
-
- 12 3月, 2019 4 次提交
- 11 3月, 2019 10 次提交
-
-
由 luotao1 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
由 sneaxiy 提交于
test=develop
-
由 sneaxiy 提交于
test=develop
-
由 sneaxiy 提交于
test=develop
-
由 tink2123 提交于
test=develop
-
由 Tink_Y 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
- 10 3月, 2019 1 次提交
-
-
由 tink2123 提交于
test=develop
-
- 08 3月, 2019 10 次提交
-
-
由 tensor-tang 提交于
test=develop
-
由 Yiqun Liu 提交于
Make parent_idx a dispensable output for beam_search op to support models saved by older paddle version. (#16106) test=develop
-
由 nhzlx 提交于
test=develop
-
由 nhzlx 提交于
test=develop
-
由 nhzlx 提交于
1). add static trt load model 2). fix bug: when device_id is not 0, the trt will have a bug test=develop
-
由 nhzlx 提交于
add simple static mode loading test=develop
-
由 nhzlx 提交于
test=develop
-
由 nhzlx 提交于
-
由 nhzlx 提交于
1. bind trt input and output to fluid tensors
-
由 Yiqun Liu 提交于
Make parent_idx a dispensable output for beam_search op to support models saved by older paddle version. (#16106) test=develop
-
- 07 3月, 2019 9 次提交
-
-
由 tensor-tang 提交于
test=develop
-
由 Yiqun Liu 提交于
- Support setting attr in config - Support setting dtype and initializer for input in config test=develop
-
由 tensor-tang 提交于
* polish the cast op doc test=develop * follow comments test=develop * fix api.spec test=develop
-
由 Yiqun Liu 提交于
- Support setting attr in config - Support setting dtype and initializer for input in config test=develop
-
由 tensor-tang 提交于
* polish the cast op doc test=develop * follow comments test=develop * fix api.spec test=develop
-
由 jerrywgz 提交于
-
由 jerrywgz 提交于
-
由 jerrywgz 提交于
-
由 jerrywgz 提交于
-
- 06 3月, 2019 1 次提交
-
-
由 xiaolil1 提交于
* Enable INT8 ReQuantize OP test=develop * Clean code test=develop * Add comments test=develop * Revert "Clean code" test=develop This reverts commit a7a49b8a. * Modify requantize op test test=develop * fix requantize UT by moving public function to public test file. test=develop * Fix test fail due to file address change. test=develop * Change file address for requantize op. test=develop
-