- 21 9月, 2022 9 次提交
-
-
由 wenbin 提交于
* residual_no_bias * comments * more ut * fix input
-
由 Piotr Paturej 提交于
[PHI] Migrate concat+grad, expand+grad, fill_constant, nearest_interp and bilinear_interp oneDNN kernels (#45863) * Migrate concat+grad, expand+grad, fill_constant, nearest_interp_v2 and bilinear_interp_v2 oneDNN kernels to PHI * Remove old namespace variable * Fix invalid out dims error * Add mutable_data method to concat output * Add check for -1 dim before computing out_dims * Capitalize oneDNNGetDataType function name * Change fill_constant kernel to correct PHI kernel * Attempt to fix dims error * Fix fill_constant (full) kernel
-
由 zhoutianzi666 提交于
* Remove trt_reshape2_matmul_fuse_pass
-
由 Wilber 提交于
-
由 jiahongyu 提交于
-
由 Leo Chen 提交于
-
由 Nyakku Shigure 提交于
* [CodeStyle] remove tabs in cpp files * update comment format
-
由 Weilong Wu 提交于
* [Eager] polish clone interface * rm clone in python, add clone in eager_method.cc
-
由 YangZhou 提交于
* unexpose audio ParameterError * clean audio utils api
-
- 20 9月, 2022 22 次提交
-
-
由 Wangzheee 提交于
* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(1): add some funtion for embedding
-
由 Sławomir Siwek 提交于
* init * remove softmaxop * merge dev * correct dir * style
-
由 Piotr Paturej 提交于
* Convert split, pad and pad3d kernels * Convert slice+grad oneDNN fluid kernels to PHI * change out->mutable_data to dev_ctx.Alloc
-
由 jakpiase 提交于
-
由 Paulina Gacek 提交于
* First approach * Shape kernel corrected * Compilation error fixed * Resize corrected * Registered types added * Mistake corrected & types added * sum kernel deleted
-
由 zhoutianzi666 提交于
* Support matmul_v2 in PaddleTensorRT
-
由 Wangzheee 提交于
* [Paddle Inference]support n lookup_tables fuse to embeddinglayernorm(2)
-
由 zhoutianzi666 提交于
* Move ITensor construction for Weight (persistable variable) from OpConvert to TensorRTEngine.
-
由 YuanRisheng 提交于
* move_merge_selected_rows * update code
-
由 Nyakku Shigure 提交于
-
由 WangZhen 提交于
* [JitLayer]Erase out vars to avoid data rewrittinig * Fix code comments
-
由 weishengying 提交于
-
由 jiahongyu 提交于
-
由 jiahongyu 提交于
-
由 ronnywang 提交于
* [NPU] fix run_program_op, test=develop * [NPU] fix matmul_v2 in cann502, test=develop
-
由 Leo Chen 提交于
* add config * add config * follow comments * fix serial run
-
由 zyfncg 提交于
-
由 Jiabin Yang 提交于
* fix linspace error in amp * fix log * fix amp error * fix ocr error which caused by amp * add more check * rename dtype ns
-
由 HongyuJia 提交于
* polish code comments * polish data_device_transform.cc
-
由 wanghuancoder 提交于
-
由 zhoutianzi666 提交于
* fix preln_residual_bias_fuse_pass bug in TNT_small model
-
由 Wilber 提交于
* python support pass external stream * fix compile error
-
- 19 9月, 2022 5 次提交
-
-
由 zyfncg 提交于
* clear extra attr of some ops in opmaker * revert clear use_cudnn for pool * fix test_operator_desc * fix Attr interface of OperatorBase
-
由 zyfncg 提交于
* fix wrong eigen header include * fix complie bug * fix nan_inf_utils_detail * fix resource_manager * fix conv_miopen_helper
-
由 YuanRisheng 提交于
* move sum * fix ci bugs * fix ci bugs * fix set_lod bugs * fix infershape bugs * fix ci bugs * fix ci unittest bug * fix ci bugs * perfect code * update code according comment * add unittest * fix ci bugs
-
由 niuliling123 提交于
-
由 wanghuancoder 提交于
-
- 18 9月, 2022 2 次提交
-
-
由 RichardWooSJTU 提交于
-
由 YuanRisheng 提交于
* perfect softmax functor * fix compile bugs * fix ci bugs
-
- 17 9月, 2022 1 次提交
-
-
由 Yuanle Liu 提交于
-
- 16 9月, 2022 1 次提交
-
-
由 sneaxiy 提交于
* support int64 non-broadcast * support broadcast case for int64 index * fix bug * support more Arity * remove some codes * upgrade patchelf to v0.15.0 to pass CI build * fix bug * fix patchelf installation * add debug flags * remove useless codes * fix viterbi_decode and set_value op uts * remove always enable int64
-