- 26 9月, 2022 3 次提交
-
-
由 zyfncg 提交于
-
由 Jiabin Yang 提交于
* support rsqrt_p * refine code and ut * add_prim_rsqrt * fix ut
-
由 zyfncg 提交于
-
- 25 9月, 2022 1 次提交
-
-
由 sneaxiy 提交于
-
- 23 9月, 2022 8 次提交
-
-
由 Ruibiao Chen 提交于
* Add ExecutionConfig and fix last-live-op bug for standalone executor * Improve code design
-
由 dongfangshenzhu 提交于
* add phi reduce_sum test=kunlun * add fhi reduce_sum test=kunlun * add fhi reduce_sum test=kunlun
-
由 zhangbo9674 提交于
-
由 Chenxiao Niu 提交于
-
由 YuanRisheng 提交于
-
由 zyfncg 提交于
-
由 Jiabin Yang 提交于
-
由 Aurelius84 提交于
* [BugFix]Fix reduce_mean/min/sum/prod, cumsum grad_op infershape bug * fix typo * fix typo
-
- 22 9月, 2022 15 次提交
-
-
由 Chenxiao Niu 提交于
-
由 Paulina Gacek 提交于
* Sum kernel migrated to phi * Static cast added, file name changed * OneDNNGetDataType to uppercase * refactoring * AddOneDNNHandler changed to SumOneDNNHandler
-
由 zyfncg 提交于
* clear extra attrs of look_up_table_v2 in opmaker * fix bug
-
由 Piotr Paturej 提交于
* Convert slice+grad oneDNN fluid kernels to PHI * Change mutable_data to Alloc * Refactor licences
-
由 王明冬 提交于
-
由 Sławomir Siwek 提交于
* gaussian random * mkldnn to onednn renaming * fix merge conflicts * remove fluid code * onednn renaming * gelu fwd * sort activations * gelu gradient * remove unused macros * merge conflicts * fix merge conflicts * remove extra contraint from gelu op
-
由 Leo Chen 提交于
-
由 Yuanle Liu 提交于
-
由 Siming Dai 提交于
-
由 Hui Zhang 提交于
* fix sub sign reverse for mkldnn * refactor code as comment * remove useless * format code
-
由 zhoutianzi666 提交于
* fix beta bug in fill_constant_batch_size_like
-
由 Haohongxiang 提交于
* fix bugs of mp * fix bugs of mp * update * update * fix bug
-
由 carryyu 提交于
* Optimize topk's performance when k is small and input_width is large * 修改blockdim设置逻辑 * Update top_k_function_cuda.h
-
由 zyfncg 提交于
-
由 Chenxiao Niu 提交于
-
- 21 9月, 2022 13 次提交
-
-
由 ccrrong 提交于
* add fp16 support * update * update half * code format * fix unittest * fix rocm compile error * code format * code format * fix rocm compile error * fix rocm compile error
-
由 Piotr Paturej 提交于
-
由 Chen Weihang 提交于
-
由 Zhen Wang 提交于
* use cinn in the paddle inference * fix some cmake errors * Avoid division by zero in the arange_kernel. * Avoid dynamic ops. * Remove some useless codes. * Use OpTransInfo to encapsulate some codes used in the build_cinn_pass.
-
由 RichardWooSJTU 提交于
-
由 Xinger 提交于
-
由 ykkk2333 提交于
* migrate sigmoid with cross entropy, and tile xpu kernels to phi, test=kunlun * migrate add_n kernep to phi, test=kunlun
-
由 wuhuachaocoding 提交于
-
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
-