- 22 11月, 2019 3 次提交
- 21 11月, 2019 4 次提交
-
-
由 huzhiqiang 提交于
* cuda kernel for sequence_topk_avg_pooling and search_fc test=develop
-
由 Pei Yang 提交于
-
由 myq406450149 提交于
-
由 石晓伟 提交于
* fix cuda building, test=develop * remove sequence_pool from cmake because build error, test=develop
-
- 20 11月, 2019 8 次提交
-
-
由 Pei Yang 提交于
* add sequence_pool cuda kernel, test=develop * fix sequence_pool cuda,test=develop * fix and complete unittest, test=develop * fix macro of sequence_pool cuda, test=develop
-
由 juncaipeng 提交于
* fix x86 search_grnn and add unit test * add cuda search_grnn and unit test
-
由 liu zhengxi 提交于
-
由 liu zhengxi 提交于
* add stack op and its unit tests, test=develop
-
由 myq406450149 提交于
* support build C++ cuda shared lib
-
由 yiicy 提交于
* [ARM] sgemv support transA, test=develop * add sgemv ut, test=develop
-
由 Pei Yang 提交于
* add sequence_pool cuda kernel, test=develop * fix sequence_pool cuda,test=develop * fix and complete unittest, test=develop
-
由 石晓伟 提交于
* add cuda ci building, test=develop * update comments, test=develop
-
- 19 11月, 2019 6 次提交
-
-
由 yiicy 提交于
-
由 hong19860320 提交于
-
由 sangoly 提交于
-
由 zhupengyang 提交于
test=develop
-
由 huzhiqiang 提交于
* add x86 op and kernel : search_fc and sequence_topk_avg_pooling for content-dnn model test=develop
-
由 zhupengyang 提交于
* [X86] add attention_padding_mask op, x86 kernel and unit test test=develop * [CUDA] add attention_padding_mask cuda kernel and unit test test=develop
-
- 18 11月, 2019 5 次提交
-
-
由 Wilber 提交于
- add var_conv_2d cuda kernel - add var_conv_2d cuda kernel unit test - temporarily set to two input mode, remove input(ROW) and input(COLUMN)
-
由 Yuan Shuai 提交于
* Fix bug target for kHost and kARM not equal. test=develop * Fix license. test=develop * add debug -g option. test=develop * enable opencl demo. test=develop * Fix model_optimize_tool found no opencl kernel. test=develop * add more vlog. test=develop * remove macro LITE_WITH_OPENCL, LITE_WITH_FPGA in passes. test=develop * Fix valid_places in mobilenetv1_test. test=develop * Fix bug of find no real output of fetch, after tool OPs of optimzer passes. test=develop * Fix vlog as log message in model_optimize_tool. test=develop * fix miscs. test=develop * fix comment. test=develop * Fix misspell of opencl, fpga kernels name in lite/api/CMakeLists.txt. test=develop * add opencl macro in full_api of demo. test=develop
-
由 Pei Yang 提交于
add sequence_pool cuda kernel
-
由 Pei Yang 提交于
add search_group_padding op and x86 kernel
-
由 zhupengyang 提交于
* [X86][CUDA] add sequence_arithmetic op , x86 kernel, cuda kernel and unit test test=develop * add sequence_arithmetic cuda kernel unit test test=develop
-
- 17 11月, 2019 1 次提交
-
-
由 juncaipeng 提交于
* add cuda match_matrix_tensor op and test, test=develop
-
- 16 11月, 2019 1 次提交
-
-
由 hong19860320 提交于
-
- 15 11月, 2019 2 次提交
-
-
由 juncaipeng 提交于
* add search_seq_depadding x86 and cuda * add match_matrix_tensor x86 * add search_grnn x86, no test
-
由 liu zhengxi 提交于
fix the cuda bilinear and nearest precision caused by data type conversion.
-
- 14 11月, 2019 5 次提交
-
-
由 Wilber 提交于
- add var_conv_2d op - add var_conv_2d x86 kernel - add var_conv_2d x86 test
-
由 liu zhengxi 提交于
* fix the compile error for cuda and fix unit test
-
由 lijianshe02 提交于
* fix conv kernel bugs and open mobilenet ci test=develop
-
由 hong19860320 提交于
-
由 Pei Yang 提交于
* update lookup_table arm x86, test=develop * add lookup_table_v2_op for compatibility, test=develop
-
- 13 11月, 2019 5 次提交
-
-
由 Wilber 提交于
- add sequence_reverse op - add sequence_reverse kernel for x86 and cuda - add sequence_reverse_test for x86 and cuda
-
由 Wilber 提交于
add CUDAContext assignment operator to fix cuda compile bug
-
由 liu zhengxi 提交于
* add cast op for x86 platform * alter the struct to class to hide the data and alter the pointer
-
由 Wilber 提交于
- add sequence_concat op - add sequence_concat kernel for x86 and cuda - add sequence_concat_test for x86 and cuda
-
由 liu zhengxi 提交于
align the lite nearest， bilinear op to fluid on arm and cuda
-