- 19 4月, 2023 9 次提交
-
-
由 kangguangli 提交于
* fix * fix * fix * fix * fix * fix fuse group order
-
由 limingshu 提交于
* first commit * restruct c++ interface to divide linear from matmulwithcublaslt * finish building in cublaslt impl * fix code bugs * fix host cost * add some changes
-
由 huangjiyi 提交于
-
由 Wang Xin 提交于
* add autogen code support for mean_all op * bug fixed * bug fixed * bug fixed
-
由 zhangyuqin1998 提交于
* fix graph_reindex * fix * Update op_compat.yaml
-
由 huangjiyi 提交于
* update * fix bug * update * fix bug
-
由 huangjiyi 提交于
-
由 huangjiyi 提交于
* update * fix bug
-
由 Yiqun Liu 提交于
-
- 18 4月, 2023 28 次提交
-
-
由 niuliling123 提交于
-
由 zhouzj 提交于
-
由 chenxujun 提交于
* Add prelu, clip_by_norm, multi_dot tests * Fix code * Fix code
-
由 Zhang Ting 提交于
-
由 tianshuo78520a 提交于
-
由 Qi Li 提交于
-
由 Zhang Zheng 提交于
* [AMP OP&Test] Unique support float16&bfloat16 * add test
-
由 zhangyuqin1998 提交于
* reorder MatrixRank * fix * fix * fix * fix * fix
-
由 cyber-pioneer 提交于
* add gn vjp * fix 0 * fix args num * fix type * debug2 * remove unused expand * support fp16 * fix typo * fix reshape bug * test3 * test4 * fix bug3 * add comment
-
由 chenxujun 提交于
-
由 huangjiyi 提交于
* update * fix bug * update * fix bug
-
由 chenxujun 提交于
* Add split, split_with_num tests * Add randperm tests * Fix code
-
由 Galaxy1458 提交于
-
由 chenxujun 提交于
-
由 tianshuo78520a 提交于
-
由 huangjiyi 提交于
* update * revert lookup_table_op
-
由 张春乔 提交于
-
由 Meteor Liu 提交于
* rename _varbase_creator as create_tensor * rename _varbase_creator as create_tensor
-
由 GGBond8488 提交于
* add 0D output support for inalg.slogdet,test=allcase * fix zerom dime test error test=allcase * fix test error test=allcase * add static backward test, test=allcase
-
由 Ruibiao Chen 提交于
-
由 tianshuo78520a 提交于
* del read * fix * test log * fix * fix bug
-
由 JYChen 提交于
* fix the set_value error in cpu * add a unitest for set_value OP * fix platform::is_gpu_place * add todo note for set_value
-
由 Zhenghai Zhang 提交于
* add autogen code support for rnn op * fix bug * fix bug
-
由 LoneRanger 提交于
* add autogen code support for lu * fix bug * fix bug * fix bug * fix bug
-
由 ronnywang 提交于
* [CustomDevice] add c_identity op * fix use calc stream
-
由 Xiaoxu Chen 提交于
-
由 Yiqun Liu 提交于
* Implement a common AmpTestBase. * Support overload of decorate. * Change the ignore list of flake and fix an error.
-
由 zhangyuqin1998 提交于
* reorder_prior_box * fix
-
- 17 4月, 2023 3 次提交
-
-
由 Yulong Ao 提交于
-
由 tianshuo78520a 提交于
* mv ps distributed dir * fix * add del auto_parallel * add auto_parallel * fix ps * fix bug * fix test bug * fix test bug * merge develop fix error * merge develop fix error * merge develop fix error
-
由 zhoutianzi666 提交于
* initial commit for cutlass_teller * second commit for cutlass_teller * add conv2d_depthwise python template * add conv2d_depthwise cutlass template * /zhoukangkang/paddle_cutlass/Paddle/paddle/fluid/framework/ir/cutlass_teller.h * refine code in Conv2dFusionCanSupport * add macro in cutlass_teller.h * add 3x3 5x5 teller * add groups not 1 or conv2d_depthwise teller * 只生成ic是8的倍数的conv2d_depthwise 的kernel * add EXPLICIT in cutlass_teller.h * final commit * add split_k_slices in conv2d_depthwise * make stages == 2 * 重构部分代码 * add CutlassFusionType * solve illegal memory * make stride_h=stride_w && make dilation==1 * must check HasAttr(use_cutlass) before GetAttrIfExists * add CONV2D_DEPTHWISE_BIAS_SILU to OpType2String * modify decl.h and util.cu
-