- 22 7月, 2020 1 次提交
-
-
由 hong19860320 提交于
* [Core][ARM] Fix beam_search, eltwise_mul supports broadcast and int64_t data type, add print op and kernel, add exeception test=develop * Fix the dims of parent idx of the arm kernel of beam_search op * elementwise_mul supports int64_t data type with broadcasting * Add print op and kernel for debugging * Support throwing the exception when the internal error occurs * Refine while and conditional_block op kernel * Support the graph optimization on subblocks * Pass program_desc and block_idx into the kernel of the control flow ops(while/conditional_block/subgraph), and create the RuntimeProgram online, it make it possiable to call the control flow ops recursively *Add unit test for masked transformer model
-
- 16 7月, 2020 1 次提交
-
-
由 MaxwellDing 提交于
-
- 13 7月, 2020 1 次提交
-
-
由 Qi Li 提交于
* [NPU] apply npu cache offline model to other devices, test=develop * [NPU] address review comments, test=develop
-
- 10 7月, 2020 1 次提交
-
-
由 MaxwellDing 提交于
add op lrn norm gather
-
- 09 7月, 2020 2 次提交
-
-
由 MaxwellDing 提交于
add mlu kernels argmax, flatten, slice, transpose
-
由 MaxwellDing 提交于
add mlu kernel dropout split squeeze reshape
-
- 06 7月, 2020 1 次提交
-
-
由 MaxwellDing 提交于
-
- 28 5月, 2020 1 次提交
-
-
由 T8T9 提交于
* reduce .so size. test=develop * compile all targets when LITE_ON_TINY_PUBLISH=OFF * unordered_map is more convenient when key is customized class * test=develop
-
- 15 4月, 2020 1 次提交
-
-
由 MaxwellDing 提交于
refactor(*): reduce Wsign-compare warning
-
- 09 4月, 2020 1 次提交
-
-
由 jackzhang235 提交于
[MLU] add some basic support for MLU, including related passes, kernels, gtests and some api in padddle_api.h Passes:mlu_subgraph_pass ,mlu_postprocess_pass Kernels: act,batch_norm, concat, conv, elementwise, fc, interpolate, pool, scale, softmax
-
- 06 3月, 2020 1 次提交
-
-
由 zhangshijin 提交于
* [MLU] support resnet50 on MLU * [MLU] support resnet50 on MLU
-