platform/core/ml/nntrainer.git
2024-04-05 Seungbaek Hong[application] update llm generate function
2024-04-05 Boseong SeoReformat code with .clang_format
2024-04-05 Boseong Seo[ BugFix ] Modify the wrong input in `EXPECT_EQ`
2024-04-05 Boseong SeoUse parameterized test in unittest
2024-04-05 kimhan0515Fix typo in docs
2024-04-05 hyeonseok lee[layer] multi batch incremental forwarding
2024-04-04 Debadri Samaddar[OpenCL] Added stringification macro and kernel path
2024-04-04 Debadri Samaddar[OpenCL] Added opencl kernel path as option
2024-04-04 Debadri Samaddar[OpenCL] Proper cleanup and readability
2024-04-04 Debadri Samaddar[OpenCL/GPU] Kernel binary caching
2024-04-04 Eunju Yang[LoRA] Apply Inception-LoRA
2024-04-04 Eunju Yang[ Trivial ] apply clang-format to fc_layer.cpp
2024-04-04 Eunju Yang[ trivial ] fix doxgen tag check error
2024-04-04 Eunju Yang[ trivial ] apply clang-format
2024-04-04 Eunju Yang[LoRA/Trivial] fix typo and edit comments
2024-04-04 Eunju Yang[LoRA] Revise LoRA implementation for fc_layer
2024-04-04 Eunju Yang[LoRA] revise type of LoraRank property & fix error...
2024-04-04 Eunju Yang[LoRA] update node_exporter of fully connected layer
2024-04-04 Eunju Yang[LoRA] add a new feat(lora) to fc layer
2024-04-03 Donghak PARK[Layer] Create Depthwise 2D Convolution
2024-04-03 skykongkong8[ neon ] Apply kernel based hgemm
2024-04-03 skykongkong8[ Trivial ] Fix typo
2024-04-03 skykongkong8[ hgemm ] Use optimized hgemm if possible
2024-04-03 skykongkong8[ hgemm ] Implement 8x8 hgemm kernel
2024-04-03 skykongkong8[ hgemm ] Implement 4x8 hgemm kernel
2024-04-03 heka1024Fix typo in test
2024-04-03 skykongkong8[ HGEMM/draft ] Draft of kernel-based hgemm
2024-04-01 Donghyeon Jeong[Coverity] Fix coverity issues
2024-03-28 Seungbaek Hong[svace] fix svace issues
2024-03-28 Donghyeon Jeong[Coverity] Fix coverity issues
2024-03-28 Donghak PARK[Trivial] Disable cpp-linter action's clang-format
2024-03-28 hyeonseok lee[coverity] fix coverity issues
2024-03-27 Donghak PARK[ coverity ] Fix Coverity issue
2024-03-26 Eunju Yang[coverity] fix coverity issue
2024-03-26 Seungbaek Hong[coverity] fix coverity issue
2024-03-25 Donghyeon Jeong[Coverity] Fix the coverity issue
2024-03-23 heka1024Fix minor errors in github action
2024-03-22 skykongkong8[ coverity ] Fix coverity issue
2024-03-19 heka1024Use parameterized test in `NamePropertyTest`
2024-03-19 GyeongHoe KooBump actions/checkout in Ubuntu Meson build & test
2024-03-19 Eunju Yang[coverity] fix coverity issues
2024-03-19 Donghyeon Jeong[Coverity] Fix the coverity issue
2024-03-15 Donghyeon Jeong[Layer] Remove Tensor setDataType() usuage
2024-03-15 skykongkong8[ neon/trivial ] Use N8 for hgemm, and for starting...
2024-03-15 skykongkong8[ neon ] Use bigger kernel in hgemv
2024-03-15 skykongkong8[ neon ] Use N8 for shorter code
2024-03-14 Donghyeon Jeong[TensorV2] Completed integration of remaining functions...
2024-03-14 Donghyeon Jeong[TensorV2] Feature Scaling Functions
2024-03-14 skykongkong8[ Tensor ] Apply fallback blas operations in Tensor...
2024-03-14 skykongkong8[ Tensor ] Apply fallback blas operations in Tensor...
2024-03-14 skykongkong8[ Tensor ] Use ele_mul instead of std::transform with...
2024-03-14 skykongkong8[ BLAS ] Remove beta condition for fallback function...
2024-03-14 Donghyeon Jeong[TensorV2] Add utility member functions to TensorV2...
2024-03-13 Debadri Samaddar[build] Updated Android build script for OpenCl inclusion
2024-03-11 Donghyeon Jeong[TensorV2] Add functions to split and concatenate tensors
2024-03-11 skykongkong8[ bugfix ] Fix wrong input when hgemv_transpose
2024-03-08 Donghak PARK[Trivial/CI] sync cpp-linter version with clang-format
2024-03-07 Donghyeon Jeong[TensorV2] Average Tensor element by axes
2024-03-07 Debadri Samaddar[OpenCL] Reduced ifdef checks
2024-03-07 Debadri Samaddar[OpenCL] CI issues fixed for clang and doxygen
2024-03-07 Debadri Samaddar[OpenCL] Addressed review comments
2024-03-07 Debadri Samaddar[OpenCL] Added doxygen comments
2024-03-07 Debadri Samaddar[GPU] Added unit test for cl_context
2024-03-07 Debadri Samaddar[GPU] Added cl_context and compute engine information
2024-03-07 Debadri Samaddar[OpenCL]Refactored example tensor GPU ops
2024-03-07 Debadri Samaddar[OpenCL] enable-opencl flag added to build option
2024-03-07 Debadri Samaddar[GPU] Sum tensor signature updated for GPU operation
2024-03-07 Debadri Samaddar[GPU] Added OpenCL interface for OpenCL tensor operations
2024-03-07 Debadri Samaddar[OpenCL] OpenCL GPU wrappers added
2024-03-05 skykongkong8[ util ] Use proper STL in max element comparison
2024-03-05 skykongkong8[ util ] Implement exp_i function
2024-03-05 skykongkong8[ util ] Use max value in softmax function
2024-03-05 skykongkong8[ util ] Implement max function in util_simd
2024-03-05 skykongkong8[ util ] Implement softmax function in util_simd
2024-03-04 Donghyeon Jeong[TensorV2] Tensor element summation by axes feature
2024-03-04 Donghak PARK[util] Add numpy file reader
2024-03-04 Donghyeon Jeong[TensorV2] Create a mask of dropout, filter, and zoneout
2024-02-28 Donghyeon Jeong[Coverity] Fix the coverity issue
2024-02-27 Jiho Chu[Android] Fix for cxxflags
2024-02-27 Donghyeon Jeong[AVX] Added VCVT (between floating-point and integer...
2024-02-23 Jiho Chu[SPEC] support neon enable option
2024-02-23 Donghyeon Jeong[TensorV2] Add Transpose Support for Tensor
2024-02-23 skykongkong8[ TensorV2 ] Apply changes made from ele-wise SIMD...
2024-02-23 skykongkong8[ BLAS ] Fix beta comparing logic
2024-02-23 skykongkong8[ BLAS ] Consider NaN case of output vector
2024-02-23 skykongkong8[ bugfix/Tensor ] Wrong practice in elementwise vector...
2024-02-23 skykongkong8[ BLAS ] Implement ele_sub, ele_div functions
2024-02-23 skykongkong8[ BLAS ] Add ele_sub and ele_div function structure
2024-02-23 skykongkong8[ NEON ] Implement ele_sub, ele_div functions
2024-02-23 skykongkong8[ trivial ] Fix formula in function brief of elementwis...
2024-02-23 skykongkong8[ NEON ] Add ele_sub and ele_div function structure
2024-02-23 skykongkong8[ BLAS ] Add scalar multiplier in elementwise operations
2024-02-23 skykongkong8[ BLAS ] implement elementwise vector multiplication...
2024-02-23 skykongkong8[ trivial ] Add parenthesis at function in another...
2024-02-23 skykongkong8[ bug ] Specify unsigned int
2024-02-23 skykongkong8[ neon ] Remove unused variable
2024-02-23 skykongkong8[ test ] Add more test cases for half-precision GEMM...
2024-02-23 skykongkong8[ BLAS ] Enable multithreading in neon GEMM, GEMV
2024-02-23 Donghyeon Jeong[TensorV2] Subtraction support
2024-02-23 Donghyeon Jeong[TensorV2] Add dot product support
next