- 14 8月, 2023 1 次提交
-
-
由 cyberslack_lee 提交于
-
- 10 8月, 2023 1 次提交
-
-
由 csy0225 提交于
-
- 09 8月, 2023 2 次提交
-
-
由 Xinyu Chen 提交于
* onednn: rename macro to PADDLE_WITH_DNNL * onednn: rename macro to CINN_WITH_DNNL
-
由 Ruibin Cheung 提交于
-
- 07 8月, 2023 3 次提交
-
-
由 Yuanle Liu 提交于
* fix cudnn 8.7+ bug on cudnnConvolutionBiasActivationForward * save_optimized_model_pass support tensorrt * update * update * fix compile * update * fix ut timeout
-
由 gouzil 提交于
-
由 Ruibin Cheung 提交于
-
- 04 8月, 2023 2 次提交
-
-
由 Ruibin Cheung 提交于
* [clang-tidy] enable modernize-use-emplace * Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into modernize_use_emplace
-
由 Zhenghai Zhang 提交于
-
- 03 8月, 2023 2 次提交
- 02 8月, 2023 3 次提交
-
-
由 wz1qqx 提交于
-
由 yangjianfengo1 提交于
[Inference] Replace groupNorm when data types are bf16 and fp16, and data format is NHWC implementation. (#55399) * finish * cpergroup odd * fix bf16 * single channel * code style * jingdu duiqi * add head_file * add bf16 head file * bf16 2 * bf16 * bf16 head * bf16 compile * py test * bf16 compile * bf16 compile * unset py test * nhwc * test * mean var * bf16 success * su * ctest success * use is_same_as * is_same * use is_same * rtol * gpu_stream * del sigmod * fix bfloat16 type * use cuda_bf16_hpp * use_cuda_arch * bfloat162float2 * del inplace_tol * del max_releative_tol * temp store * jingdu duiqi * temp store * plugin * jingdu duiqi * duiqi * include cuda.h * del half * half single * ci * add const * ci * cudamemset * del printf * fp16 test * add half compute * del br16 ci * del ci * ci approve * del fluid include
-
由 jiangfan06 提交于
-
- 01 8月, 2023 1 次提交
-
-
由 hong19860320 提交于
-
- 27 7月, 2023 2 次提交
- 24 7月, 2023 2 次提交
-
-
由 chen 提交于
[Paddle-TRT] Convert 0D tensor to 1D tensor, increase the shape tensor's number count when collecting shape (#55503) * make 0-D tensor to 1-D tensor to support Grounding-SAM and add shape check * recover identity_op_clean_pass.cc
-
由 Xinyu Chen 提交于
* onednn: remove fc+eltwiseadd fusion pass * onednn: remove post-sum fusion in fc kernel * onednn: tests: make unfused add run into f32
-
- 21 7月, 2023 3 次提交
-
-
由 Yuanle Liu 提交于
* fix cudnn 8.7+ bug on cudnnConvolutionBiasActivationForward * save_optimized_model_pass support gpu
-
由 Ruibin Cheung 提交于
-
由 Jeng Bai-Cheng 提交于
Issue #55016
-
- 20 7月, 2023 2 次提交
-
-
由 Leo Chen 提交于
* Fix TRT multihead matmul UT failure
-
由 zhupengyang 提交于
-
- 19 7月, 2023 2 次提交
- 17 7月, 2023 2 次提交
-
-
由 iamsonderr 提交于
* support_conv2d * remove comment * check code style * add former Test * check code style * add unittest * fix log * change unittest --------- Co-authored-by: zhoutianzi666 <17801055074@163.com>
-
由 ming1753 提交于
* [Paddle-TRT] add assign op
-
- 13 7月, 2023 1 次提交
-
-
由 Yuanle Liu 提交于
* copy dense_tensor.h to inference lib * update * update
-
- 12 7月, 2023 3 次提交
-
-
由 Yuanle Liu 提交于
* rewrite identity_op_clean_pass * fix * adjust identity_op_clean_pass order in gpu passes * fix ut
-
由 YangQun 提交于
* squash pick the poc code * fix build after rebase * fix int8 conv and fc uts * Fix and clean-up Get_SRC_Scale_Memory * fix floating point fc uts * fix test_analyzer_int8_googlenet * test_analyzer_int8_mobilenetv1 * fix int8 mobilenet v2 and v3 * fix build error after rebase * [oneDNN] rename library version * fix conv bias datatype * try to fix import error * fix rebase error * [oneDNN] pack library into python wheel * add MKLDNN_SHARED_LIB_3 to env_dict * fix test_analyzer_bert * fix fill_constant op kernel * fix ernie and matmul op ut * fix softplus ut * fix conv+relu6 fusion ut * fix hardswish fusion * fix quant+transpose fusion ut * fixsgd ut * fix int8 matmul with flatten * fix fc+scale fusion * fix conv/matmul+gelu fusion uts * fix rebase error * Revert "fix conv/matmul+gelu fusion uts" This reverts commit 47eb5e49972bd8f7271a233def9bfb3e98ce78e1. * upgrade to onednn v3.1 * remove older version onednn * use densetensor::data() for achieving mean and var in layernorm impl * comments for atol of integer tests * fix clang-format * Revert "remove older version onednn" This reverts commit 783e57ddfd4401254596eae7d47adb9b03590c09. * improve binary handle * fix expand kernel * Revert "use densetensor::data() for achieving mean and var in layernorm impl" * always use forward_inference for conv * remove activation scales * rollback changes to mkldnn.cmake * address comments * port changes to dequantize kernel * fix merge error * fix fused_elementwise_kernel * upgrade onednn version to v3.1.1 * fix some approval error * fix error msg format * remove old onednn libs * try to fix symbolic link issue * fix cinn test case segfault * do not explicit link test with onednn * remove unnecessary changes * integrate CINN with onednn v3 * link with mkldnn project * fix cinn build file --------- Co-authored-by: NTomasz Socha <tomasz.socha@intel.com> Co-authored-by: NChen, Xinyu1 <xinyu1.chen@intel.com> Co-authored-by: Ntianshuo78520a <707759223@qq.com>
-
由 Wang Xin 提交于
* [clang-tidy] enable readability-container-size-empty check * fix test_custom_kernel Failed * add clang-tid-10 in dockerfile * add clang-tidy in dockerfile * fix bug
-
- 07 7月, 2023 4 次提交
-
-
由 wz1qqx 提交于
-
由 wz1qqx 提交于
-
由 Yuanle Liu 提交于
* fix WITH_SHARED_IR option type * rename WITH_INFERENCE_NVTX to WITH_NVTX and fix compile bug * update
-
由 iamsonderr 提交于
* commit * del inplace op in memory_optimize_pass.cc * check code style
-
- 06 7月, 2023 1 次提交
-
-
由 zhupengyang 提交于
-
- 05 7月, 2023 1 次提交
-
-
由 wz1qqx 提交于
-
- 04 7月, 2023 1 次提交
-
-
由 Leo Chen 提交于
-
- 03 7月, 2023 1 次提交
-
-
由 周周周 提交于
* commit * commit * commit * commit * final commit * use hook to collect shape and shape value
-