- 15 5月, 2023 1 次提交
-
-
由 risemeup1 提交于
-
- 12 5月, 2023 2 次提交
-
-
由 ronnywang 提交于
-
由 Ruibiao Chen 提交于
* Skip fake alloc in static build for depend and nop op * Skip communication op * Skip sync op
-
- 11 5月, 2023 4 次提交
-
-
由 lanxianghit 提交于
添加CINN与Paddle框架的BFloat16类型映射
-
由 Yuanle Liu 提交于
* prelu op trt converter support zero dim
-
由 jjyaoao 提交于
-
由 张春乔 提交于
-
- 10 5月, 2023 2 次提交
-
-
由 wz1qqx 提交于
* fix as review, add fp16 conv2d_transpose * fix unittest of bn and reduce_mean * fix bn unittest * fix ci * fix ci
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop
-
- 09 5月, 2023 3 次提交
-
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop
-
由 zhoutianzi666 提交于
* delete delete_fill_constant_op_pass and unsqueeze2_eltwise_fuse_pass
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop
-
- 08 5月, 2023 3 次提交
-
-
由 kangguangli 提交于
-
由 张春乔 提交于
-
由 wz1qqx 提交于
-
- 05 5月, 2023 2 次提交
-
-
由 shentanyue 提交于
-
由 sprouteer 提交于
-
- 04 5月, 2023 1 次提交
-
-
由 weishengying 提交于
-
- 28 4月, 2023 1 次提交
-
-
由 HongyuJia 提交于
-
- 27 4月, 2023 4 次提交
-
-
由 zhupengyang 提交于
-
由 wuhuachaocoding 提交于
-
由 HongyuJia 提交于
* [CINN Support 0D-Tensor] CINN supports 0D-Tensor with trick temporarily * Add unittest
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop
-
- 26 4月, 2023 1 次提交
-
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop
-
- 25 4月, 2023 3 次提交
-
-
由 sprouteer 提交于
-
由 wuhuachaocoding 提交于
-
由 YuanRisheng 提交于
* add flags for phi * fix compile bugs * fix ci bugs * fix inference bugs * fix cinn' bugs * fix cinn bugs * perfect code according comment * fix ci bugs * fix ci bugs
-
- 24 4月, 2023 4 次提交
-
-
由 niuliling123 提交于
-
由 zhupengyang 提交于
-
由 张春乔 提交于
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test ,test=develop
-
- 23 4月, 2023 2 次提交
-
-
由 risemeup1 提交于
* apply gcc12 to gpups * apply gcc12 to gpups * apply gcc12 to gpups * apply gcc12 to gpups * apply gcc12 to gpups * apply gcc12 to gpups * apply gcc12 to gpips * apply gcc12 to gpups * apply gcc12 to gpups * test * test * apply gcc12 to gpups * apply_gcc12_to_gpups * fix compiler bug * fix compiler bug * test * fix dangling-pointer compiler * fix dangling-pointer compiler * fix dangling-pointer compiler * apply_gcc12_to_gpups * apply gcc12 to gpups * Update cuda_streams_py.cc
-
由 Galaxy1458 提交于
* test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop * test,test=develop
-
- 21 4月, 2023 4 次提交
-
-
由 JYChen 提交于
* support 0-D output and 0-D as indice in __getitem__ * fix tests * fix inference and UT * add unittest for setitem * fix xpu test * fix xpu 0-d
-
由 YuhangLi 提交于
-
由 Ghost Screaming 提交于
* Fix bug of reduce_sum op. When input.numel() > INT32_MAX, its result is wrong. * Remove climits. * Fix bug of BlockDesc::MoveFrom(). It's used to rebuild main_program_desc from ProgramDesc modified by Fusion Pass. As some fused operators need to create new Variables in modified ProgramDesc, MoveFrom function uses std::move() function to move these VarDesc to main_program_desc. As a result, their pointers holded by modified ProgramDesc become nullptr. When call block()->Program()->proto() function, it will call ProgramDesc::Flush() function at first, which may cause a segmentation fault.
-
由 zhupengyang 提交于
-
- 20 4月, 2023 3 次提交
-
-
由 tianshuo78520a 提交于
This reverts commit 543efcc5.
-
由 HongyuJia 提交于
* [CustomOP error] Add attrs type check * fix global variable order bug * include unordered_set * fix ParseAttrStr compile error
-
由 huangjiyi 提交于
* update * update * Revert "update" * fix bug * update
-