- 28 1月, 2019 2 次提交
-
-
由 Qiao Longfei 提交于
-
由 Qiao Longfei 提交于
-
- 27 1月, 2019 3 次提交
-
-
由 Qiao Longfei 提交于
-
由 Qiao Longfei 提交于
-
由 Qiao Longfei 提交于
-
- 26 1月, 2019 7 次提交
-
-
-
由 Qiao Longfei 提交于
-
由 gongweibao 提交于
-
由 Tao Luo 提交于
Refine INT8 calibration API
-
由 Tao Luo 提交于
move ngraph_bridge to ngraph directory
-
由 Yan Chunwei 提交于
-
由 baojun-nervana 提交于
-
- 25 1月, 2019 13 次提交
-
-
-
由 ruri 提交于
Add Shuffle Channel Operator
-
由 Haihao Shen 提交于
-
由 tensor-tang 提交于
jit benchmark use tensor with alignment
-
由 乔龙飞 Qiao Longfei 提交于
Optimize cpp reader
-
由 gongweibao 提交于
-
由 gongweibao 提交于
-
由 tangwei12 提交于
* fix mistakes in merge_ids, test=develop
-
由 Zhaolong Xing 提交于
Add check: conv_fusion op runs with cudnn version > 7100 .
-
由 baojun 提交于
* enable ngraph_engine_op test=develop * merge develop test=develop * avoid const_cast test=develop * rm ngraph_operator test=develop * Added TODO to move EnableNgraph test=develop * Add TODO to remove const_cast test=develop
-
由 chengduo 提交于
test=develop
-
由 chengduo 提交于
* Revert "set constant for loss" This reverts commit 167933f678ccbb3563e949710279efe004a27731. * Revert "remove workspace_handle" test=develop This reverts commit b4aca8ede9e685bce1dfb1c59e63919f33432572.
-
由 tensor-tang 提交于
test=develop
-
- 24 1月, 2019 15 次提交
-
-
由 Yiqun Liu 提交于
* Refine the beam_search op and test. * A basic CUDA implementation of beam_search for small batch_size. * Implement CUDA kernel for beam_search_op. * Use multiple CUDA threads in the same block to select the top beam. * Update the python api of beam_search op. * Enable extend function in CPU kernel of beam_search op. * Unify the CUDA codes. test=develop * Unify the CPU kernel of beam_search op. * Ensure the seletced items of beam_search_op's CPU kernel sorted by scores. * Update the description of beam_search in API.spec. * Enable the use of CUDA kernel in beam_search op. * Exclude the beam_search's CUDA unittest when there is no CUDA gpu, and delete some debuging statements. test=develop * Follow comments. test=develop * Call the CPU kernel for beam_search op when batch_size > 4. test=develop * Remove the except of is_empty op in PrepareData. test=develop
-
由 Zeng Jinle 提交于
Disable eager deletion unittest temporarily since random failure.
-
由 Zeng Jinle 提交于
Fix bug when user set CUDA_VISIBLE_DEVICES be empty and run CPU-only models
-
由 Wu Yi 提交于
-
由 Zeng Jinle 提交于
Turn on remove_unnecessary_lock by default
-
由 chengduo 提交于
test=develop
-
由 tangwei12 提交于
* nce add check sample lables, test=develop
-
由 sneaxiy 提交于
-
由 nhzlx 提交于
test=develop
-
由 nhzlx 提交于
Add check for it. test=develop
-
由 tensor-tang 提交于
fix debug compile issue of analysis pass
-
由 liuwei1031 提交于
* fix github issue 15267 test=develop * fix github issue 15267 test=develop * monitor the GPU usage during runtime * revert allocator_facade.cc change * comments update test=develop
-
由 Xin Pan 提交于
Imperative Resnet
-
由 sneaxiy 提交于
test=develop
-
由 sneaxiy 提交于
test=develop
-