- 01 2月, 2023 32 次提交
-
-
由 RedContritio 提交于
* add range check for crop_kernel * remove shape negative check * add unittest
-
由 RedContritio 提交于
* add shape check for fused_multi_head_attention * use raise for coverage test * add unittest * remove unnecessary pass * add unittest
-
由 RedContritio 提交于
* add check for input of slice * add unittest
-
由 pangyoki 提交于
* fix release dockerfile * fix GPG error in ubuntu18 * fix cpu * fix
-
由 pangyoki 提交于
* support python3.10 in manylinux dockerfile * fix python3.10 ssl * do not check for python3.10
-
由 pangyoki 提交于
-
由 RedContritio 提交于
* add stride check for MaxPool * add unittests
-
由 Zhong Hui 提交于
* fix 0-d tensor for arg_min_max op. * fix xpu. * fix zero dims * fix * Update arg_min_max_kernel.cc * Update arg_min_max_kernel.cc * Update arg_min_max_kernel.cc * Update test_zero_dim_tensor.py * Update test_zero_dim_tensor_xpu.py * Update test_zero_dim_tensor.py * Update arg_min_max_kernel.cc * Update arg_min_max_kernel.cc * Update arg_min_max_kernel.cc
-
由 YUNSHEN XIE 提交于
* run infer ut in A10 * 增加cuda11.2-cudnn8-trt8.4镜像 * add paddle_coverage_new.sh
-
由 PuQing 提交于
* fix numpyScaler2Tensor type error * fix to_tensor docs, test=document_fix
-
由 Guanghua Yu 提交于
-
由 张春乔 提交于
* fix the div 0 error of sparse_embedding * add unittest
-
由 张春乔 提交于
-
由 Wang Bojun 提交于
* preln_residual 2 fused_bias_residual * skip layernorm fix and ut * code refine * code style refine * fix ut * fix output * add trt layer fall back info * refine op teller and ut * DropoutMaskOut output fix
-
由 Hui Zhang 提交于
* jit layer support multi thread * fix bug * clone prediector not do graph optimizer * format * fix comment and format * fix override and fromat * fix * fix
-
由 RedContritio 提交于
* add dimension check for deformable_conv * add unittest
-
由 MarDino 提交于
-
由 zhangyikun02 提交于
-
由 gouzil 提交于
* [Divide by 0 Error] add lu check * [Divide by 0 Error] lu check migrate to c++
-
由 Ruibiao Chen 提交于
-
由 gouzil 提交于
* [Divide by 0 Error] add eig check * [Divide by 0 Error] eig check migrate to c++ * [Divide by 0 Error] Fix class name error
-
由 gouzil 提交于
* [Divide by 0 Error] add norm check * [Divide by 0 Error] fix x AttributeError * [Divide by 0 Error] norm check migrate to c++
-
由 limingshu 提交于
* A leap of try for cudaLaunchCooperativeKernel * fix bugs * Totally replace the lar cuda kernel * Fix bugs * fix code according to comments * fix codes according to review comments * adding some function overload * relocate the power operation. * add bf16 support for index select relevant ops * revert bf16 type change. * add changes for more op * fix code writting bugs
-
由 zhoutianzi666 提交于
-
由 wangxiaoning 提交于
-
由 zqw_1997 提交于
-
由 zxcd 提交于
* add clip_grad_norm_ api. * fix docs and some details according to the comments. * fix code style. * fix no_grad problem, and fix doc. * fix code style. * fix doc and remove type information
-
由 RedContritio 提交于
* add axis check for unbind * add axis range check for unbind * update unittest and axis validation for unbind * add unittest invalid axis for unbind * restore axis extract for unbind
-
由 RedContritio 提交于
-
由 LiYuRio 提交于
-
由 Aurelius84 提交于
* [PrimCinn]Fix some vars are wrongly gc in CINN+InterpreterCore * fix baseline unittest config * fix code style
-
由 limingshu 提交于
* profile reduce kernel for fp16 and reduceHigherdim * use reinterpret_cast * fix for CI on ROCm * add Macro for ROCm * ROCm CI config * ROCm CI config * unit test repair * pull * add common_funcs.h * reduceType * Update reduce_function.h * not higher * rename * implement of matmul using cublasLt instead of cublas * cublasLt bugfix * Update matmul_kernel_impl.h * Update matmul_kernel_impl_via_blasLt.h * for-loop-algo * PR comments changes * add macro * ci unused variable isCublasLt * ci unused variable isCublasLt macro * split matmul to autotune * rewrite the split kernel with segmented_array * rewrite the split kernel with segmented_array * rewrite the split kernel with segmented_array * add some method for cuda_graph * fix bugs for rocm * change for ci-error * i dont know why ci-model-benchmark gives a shit error, so i recover codes with original one to see if original codes work. * add some changes for passing mode_benchmark and coverage ci * fix ci error * fix ci-rocm error * add some changes for header --------- Co-authored-by: Nzhangbopd <1299246947@qq.com> Co-authored-by: NBo Zhang <105368690+zhangbopd@users.noreply.github.com>
-
- 31 1月, 2023 8 次提交
-
-
由 RedContritio 提交于
-
由 wenbin 提交于
* gn_silu * add ut * set TIMEOUT * correct comments * comments * disable windows ut * rename parameter
-
由 姜永久 提交于
* check dygraph on for op tests * reset eigh and modify prelu&sign * update eager_op_test * lint * add more ops * fix reduce * modify reduce test * reset reduce_op * modify matmul test * revert prelu
-
由 姜永久 提交于
* update elementwise ops tests * add more ops * modify sum&split * lint * rm check_dygraph * revert pow * modify add for cpu test * revert reshape * modify min
-
由 姜永久 提交于
* more ops * revert some ops * reset some ops
-
由 wangshengxiang 提交于
-
由 wenbin 提交于
* disable integer * disable integer * add cast layer
-
由 Zhang Jun 提交于
-