- 19 11月, 2018 12 次提交
-
-
由 qingqing01 提交于
* Modify some infer-shape in compile-time.
-
由 Tao Luo 提交于
[WIP] Correcting and extending MKLDNN residual connection fuse pass
-
由 Yihua Xu 提交于
* Optimize layer_norm operator with AVX intrinsic functions * Revert the wrong modifications * Implement the jit kernel for layer_norm operator * Add math headfile to fix the compile issue (test=develop) * Add math headfile to fix the compile issue (test=develop) * Fixed the intrinsic headfile issue (test=develop) * Fix the conflicts (test=develop) * Revert for CUDA compiler (test=develop) * Fixed the cuda depency (test=develop) * Fix the marco issues (test=develop)
-
由 Houjiang Chen 提交于
Fix tensorrt plugin cmake dependency, test=develop
-
由 Yu Yang 提交于
Rewrite allocation
-
由 hjchen2 提交于
-
由 qingqing01 提交于
* Convolution fusion operator. * Clean code test=develop
-
-
由 Yu Yang 提交于
test=develop
-
由 Yu Yang 提交于
test=develop
-
由 Wu Yi 提交于
* fix dist deps test=develop * update test=develop * update test=develop * update test=develop * update test=develop
-
由 Yu Yang 提交于
test=develop
-
- 18 11月, 2018 1 次提交
-
-
由 Qiao Longfei 提交于
optimize distribute checkport
-
- 17 11月, 2018 2 次提交
-
-
由 Qiao Longfei 提交于
-
由 Qiao Longfei 提交于
test=develop
-
- 16 11月, 2018 25 次提交
-
-
由 tensor-tang 提交于
fix build error on noavx
-
由 tensor-tang 提交于
test=develop
-
由 Wu Yi 提交于
* wip simplify operator framework * wip * wip * done test=develop * clean test=develop * fix test=develop * fix deps test=develop * fix cpu build test=develop * fix tensorrt build test=develop * fix tests test=develop * fix test=develop * fix cpu build test=develop
-
由 Tomasz Patejko 提交于
test=develop
-
由 tensor-tang 提交于
jitcode act relu, exp, sigmoid, tanh
-
由 Jiabin Yang 提交于
* fix space_to_depth_op unicode problem * test=develop
-
由 Qiao Longfei 提交于
change the target cost of test_label_semantic_roles to speed up test
-
由 Tomasz Patejko 提交于
-
由 Tomasz Patejko 提交于
-
由 Tomasz Patejko 提交于
-
由 Tomasz Patejko 提交于
-
由 Tomasz Patejko 提交于
* implements reachability check between identity node and non-identity argument to elementwise_add * implements handling identity node as x and as y argument to elementwise_add
-
由 whs 提交于
* Fix truncated normal. * Fix. * Make nce support more distribution. * Fix API.spec. * Fix python API. * Fix. test=develop * Fix API.spec test=develop * Fix sampler. * Fix order of arguments in python API. test=develop
-
由 Qiao Longfei 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
由 Qiao Longfei 提交于
-
由 Yu Yang 提交于
test=develop
-
由 Zhaolong Xing 提交于
Add PRelu tensorRT plugin and Conv2d transpose op converter
-
由 Yu Yang 提交于
test=develop
-
由 Qiyang Min 提交于
Fix expand op incorrect infer shape
-
由 hjchen2 提交于
-
由 Wu Yi 提交于
* add cudnn ctc loss * wip add test test=develop * wip * wip * done test=develop * move include cudnn test=develop * test test=develop * fix build test=develop * fix build test=develop * fix build on cudnn5 test=develop * fix cudnn5 build test=develop * fix cudnn5 build test=develop * merge develop softmax functor change test=develop
-
由 tensor-tang 提交于
test=develop
-
由 tensor-tang 提交于
test=develop
-
由 Xin Pan 提交于
fix typo test=develop
-