Versions
v2.7.0 :: 0 :: gentoo
- Modified
- License
- BSD
- Keywords
- ~amd64
- USE flags
- cuda distributed fbgemm flash gloo memefficient mkl mpi nnpack numpy onednn openblas opencl openmp qnnpack rocm xnnpack
v2.6.0-r4 :: 0 :: gentoo
- Modified
- License
- BSD
- Keywords
- ~amd64
- USE flags
- cuda distributed fbgemm flash gloo memefficient mkl mpi nnpack numpy onednn openblas opencl openmp qnnpack rocm xnnpack
v2.5.1-r11 :: 0 :: gentoo
- Modified
- License
- BSD
- Keywords
- ~amd64
- USE flags
- cuda distributed fbgemm flash gloo memefficient mkl mpi nnpack numpy onednn openblas opencl openmp qnnpack rocm xnnpack
v2.4.1-r7 :: 0 :: gentoo
- Modified
- License
- BSD
- Keywords
- ~amd64
- USE flags
- cuda distributed fbgemm flash gloo mkl mpi nnpack numpy onednn openblas opencl openmp qnnpack rocm xnnpack
USE flags
General
- cuda
- Enable NVIDIA CUDA support (computation on GPU)
- distributed
- Support distributed applications
- fbgemm
- Use sci-ml/FBGEMM
- flash
- Enable flash attention
- gloo
- Use sci-ml/gloo
- memefficient
- Enable mem efficient attention
- mkl
- Use sci-libs/mkl for blas, lapack and sparse blas routines
- mpi
- Add MPI (Message Passing Interface) layer to the apps that support it
- nnpack
- Use sci-ml/NNPACK
- numpy
- Add support for math operations through numpy
- onednn
- Use sci-ml/oneDNN
- openblas
- Use sci-libs/openblas for blas routines
- opencl
- Enable OpenCL support (computation on GPU)
- openmp
- Use OpenMP for parallel code
- qnnpack
- Use QNNPACK
- rocm
- Enable ROCm gpu computing support
- xnnpack
- Use sci-ml/XNNPACK
amdgpu_targets
- gfx1010
- RDNA GPU, codename navi10, including Radeon RX 5700XT/5700/5700M/5700B/5700XTB/5600XT/5600/5600M, Radeon Pro 5700XT/5700, Radeon Pro W5700X/W5700
- gfx1011
- RDNA GPU, codename navi12, including Radeon Pro 5600M/V520
- gfx1012
- RDNA GPU, codename navi14, including Radeon RX 5500XT/5500/5500M/5500XTB/5300/5300M, Radeon Pro 5500XT/5500M/5300/5300M, Radeon Pro W5500X/W5500/W5500M/W5300M
- gfx1030
- RDNA2 GPU, codename navi21/sienna cichlid, including Radeon RX 6950XT/6900XT/6800XT/6800, Radeon Pro W6800
- gfx1031
- RDNA2 GPU, codename navi22/navy flounder, including Radeon RX 6750XT/6700XT/6800M/6700M
- gfx1100
- RDNA3 GPU, codename navi31/plum bonito, including Radeon RX 7900XTX/7900XT, AMD Radeon Pro W7900/W7800
- gfx1101
- RDNA3 GPU, codename navi32, including Radeon RX 7700XT/7800XT
- gfx1102
- RDNA3 GPU, codename navi33, including Radeon RX 7600/7600M/7600M XT/7700S/7600S, AMD Radeon PRO W7600/W7500
- gfx803
- Fiji GPU, codename fiji, including Radeon R9 Nano/Fury/FuryX, Radeon Pro Duo, FirePro S9300x2, Radeon Instinct MI8
- gfx900
- Vega GPU, codename vega10, including Radeon Vega Frontier Edition, Radeon RX Vega 56/64, Radeon RX Vega 64 Liquid, Radeon Pro Vega 48/56/64/64X, Radeon Pro WX 8200/9100, Radeon Pro V320/V340/SSG, Radeon Instinct MI25
- gfx906
- Vega GPU, codename vega20, including Radeon (Pro) VII, Radeon Instinct MI50/MI60
- gfx908
- CDNA Accelerator, codename arcturus, including AMD Instinct MI100 Accelerator
- gfx90a
- CDNA2 Accelerator, codename aldebaran, including AMD Instinct MI200 series Accelerators
- gfx940
- CDNA3 Accelerator, codename aqua_vangaram, MI300A rev 0
- gfx941
- CDNA3 Accelerator, codename aqua_vangaram, MI300X rev 0
- gfx942
- CDNA3 Accelerator, codename aqua_vangaram, MI300A and MI300X rev >=1
python_single_target
- python3_10
- Build for Python 3.10 only
- python3_11
- Build for Python 3.11 only
- python3_12
- Build for Python 3.12 only
- python3_13
- Build for Python 3.13 only
Dependencies
dev-cpp / abseil-cpp : Abseil Common Libraries (C++), LTS Branch
dev-cpp / cpp-httplib : C++ HTTP/HTTPS server and client library
dev-cpp / gflags : Google's C++ argument parsing library
dev-cpp / glog : Google Logging library
dev-cpp / nlohmann_json : JSON for Modern C++
dev-cpp / opentelemetry-cpp : The OpenTelemetry C++ Client
dev-lang / python : Freethreading (no-GIL) version of Python programming language
dev-libs / FXdiv : Division via fixed-point multiplication by inverse
dev-libs / clog : C-style (a-la printf) logging library
dev-libs / cpuinfo : CPU INFOrmation library
dev-libs / cudnn : NVIDIA Accelerated Deep Learning on GPU library
dev-libs / cutlass : CUDA Templates for Linear Algebra Subroutines
dev-libs / flatbuffers : Memory efficient serialization library
dev-libs / libfmt : Small, safe and fast formatting library
dev-libs / pocketfft : PocketFFT for C++
dev-libs / protobuf : Google's Protocol Buffers - Extensible mechanism for serializing structured data
dev-libs / psimd : P(ortable) SIMD
dev-libs / pthreadpool : Portable and efficient thread pool implementation
dev-libs / rccl : ROCm Communication Collectives Library (RCCL)
dev-libs / sleef : Implements vectorized versions of C standard math functions
dev-python / numpy : Fast array and numerical python library
dev-python / pybind11 : AST-based Python refactoring library
dev-python / pyyaml : YAML parser and emitter for Python
dev-python / typing-extensions : Backported and Experimental Type Hints for Python 3.7+
dev-util / hip : C++ Heterogeneous-Compute Interface for Portability
dev-util / nvidia-cuda-toolkit : NVIDIA CUDA Toolkit (compiler and friends)
dev-util / roctracer : Callback/Activity Library for Performance tracing AMD GPU's
sci-libs / hipBLAS : ROCm BLAS marshalling library
sci-libs / hipBLASLt : General matrix-matrix operations library for AMD Instinct accelerators
sci-libs / hipCUB : Wrapper of rocPRIM or CUB for GPU parallel primitives
sci-libs / hipFFT : CU / ROCM agnostic hip FFT implementation
sci-libs / hipRAND : CU / ROCM agnostic hip RAND implementation
sci-libs / hipSOLVER : CU / ROCM agnostic marshalling library for LAPACK routines on the GPU
sci-libs / hipSPARSE : ROCm SPARSE marshalling library
sci-libs / miopen : AMD's Machine Intelligence Library
sci-libs / mkl : Intel Math Kernel Library
sci-libs / openblas : Optimized BLAS library based on GotoBLAS2
sci-libs / rocPRIM : HIP parallel primitives for developing performant GPU-accelerated code on ROCm
sci-libs / rocThrust : HIP back-end for the parallel algorithm library Thrust
sci-ml / FBGEMM : Facebook GEneral Matrix Multiplication
sci-ml / FP16 : conversion to/from half-precision floating point formats
sci-ml / NNPACK : acceleration package for neural network computations
sci-ml / XNNPACK : library of floating-point neural network inference operators
sci-ml / cudnn-frontend : A c++ wrapper for the cudnn backend API
sci-ml / foxi : ONNXIFI with Facebook Extension
sci-ml / gemmlowp : Low-precision matrix multiplication
sci-ml / gloo : library of floating-point neural network inference operators
sci-ml / ideep : Intel® Optimization for Chainer
sci-ml / kineto : part of the PyTorch Profiler
sci-ml / oneDNN : oneAPI Deep Neural Network Library
sci-ml / onnx : Open Neural Network Exchange (ONNX)
sci-ml / tensorpipe : provides a tensor-aware channel
virtual / lapack : Virtual for Linear Algebra Package FORTRAN 77 (LAPACK) implementation
virtual / mpi : Virtual for Message Passing Interface (MPI) v2.0 implementation
Runtime Dependencies
dev-cpp / abseil-cpp : Abseil Common Libraries (C++), LTS Branch
dev-cpp / cpp-httplib : C++ HTTP/HTTPS server and client library
dev-cpp / gflags : Google's C++ argument parsing library
dev-cpp / glog : Google Logging library
dev-cpp / nlohmann_json : JSON for Modern C++
dev-cpp / opentelemetry-cpp : The OpenTelemetry C++ Client
dev-lang / python : Freethreading (no-GIL) version of Python programming language
dev-libs / cpuinfo : CPU INFOrmation library
dev-libs / cudnn : NVIDIA Accelerated Deep Learning on GPU library
dev-libs / libfmt : Small, safe and fast formatting library
dev-libs / protobuf : Google's Protocol Buffers - Extensible mechanism for serializing structured data
dev-libs / pthreadpool : Portable and efficient thread pool implementation
dev-libs / rccl : ROCm Communication Collectives Library (RCCL)
dev-libs / sleef : Implements vectorized versions of C standard math functions
dev-python / numpy : Fast array and numerical python library
dev-util / hip : C++ Heterogeneous-Compute Interface for Portability
dev-util / nvidia-cuda-toolkit : NVIDIA CUDA Toolkit (compiler and friends)
dev-util / roctracer : Callback/Activity Library for Performance tracing AMD GPU's
sci-libs / hipBLAS : ROCm BLAS marshalling library
sci-libs / hipBLASLt : General matrix-matrix operations library for AMD Instinct accelerators
sci-libs / hipCUB : Wrapper of rocPRIM or CUB for GPU parallel primitives
sci-libs / hipFFT : CU / ROCM agnostic hip FFT implementation
sci-libs / hipRAND : CU / ROCM agnostic hip RAND implementation
sci-libs / hipSOLVER : CU / ROCM agnostic marshalling library for LAPACK routines on the GPU
sci-libs / hipSPARSE : ROCm SPARSE marshalling library
sci-libs / miopen : AMD's Machine Intelligence Library
sci-libs / mkl : Intel Math Kernel Library
sci-libs / openblas : Optimized BLAS library based on GotoBLAS2
sci-libs / rocPRIM : HIP parallel primitives for developing performant GPU-accelerated code on ROCm
sci-libs / rocThrust : HIP back-end for the parallel algorithm library Thrust
sci-ml / FBGEMM : Facebook GEneral Matrix Multiplication
sci-ml / NNPACK : acceleration package for neural network computations
sci-ml / XNNPACK : library of floating-point neural network inference operators
sci-ml / cudnn-frontend : A c++ wrapper for the cudnn backend API
sci-ml / foxi : ONNXIFI with Facebook Extension
sci-ml / gemmlowp : Low-precision matrix multiplication
sci-ml / gloo : library of floating-point neural network inference operators
sci-ml / oneDNN : oneAPI Deep Neural Network Library
sci-ml / onnx : Open Neural Network Exchange (ONNX)
sci-ml / tensorpipe : provides a tensor-aware channel
virtual / lapack : Virtual for Linear Algebra Package FORTRAN 77 (LAPACK) implementation
virtual / mpi : Virtual for Message Passing Interface (MPI) v2.0 implementation
Depending packages
sci-chemistry / gromacs : The ultimate molecular dynamics simulation package
sci-ml / datasets : Access and share datasets for Audio, Computer Vision, and NLP tasks
sci-ml / pytorch : Tensors and Dynamic neural networks in Python
sci-ml / torchvision : Datasets, transforms and models to specific to computer vision
sci-ml / transformers : State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow
Bugs
- 947933
- sci-ml/pytorch: stop "unbundling" sci-ml/caffe2
- 950463
- sys-devel/gcc-14.2.1_p20241221: ICE when building sci-ml/caffe2 on arm64
- 953366
- sci-ml/caffe2-2.6.0-r3 - [llvm] strong_type.h: error: is_arithmetic cannot be specialized: Users are not allowed to specialize this standard library entity [-Winvalid-spe
- 954772
- sci-ml/caffe2-2.7.0 build failure with gcc-15 (HIP kernels hit __glibcxx_assert_fail in __host__ __device__)
Change logs
- Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/caffe2: add 2.7.0
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: move dev-libs/cudnn-frontend to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Sv. Lockal · gentoo
sci-ml/caffe2: fix build for ROCm
* Revised the fix for `-fclang-abi-compat=17`. * Added fixes for libc++ Closes: https://bugs.gentoo.org/953101 Signed-off-by: Sv. Lockal <lockalsash@gmail.com> Closes: https://github.com/gentoo/gentoo/pull/41448 Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: back to single. (multi does not work)
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: moving caffe2 from python-single-r1 to python-r1
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/caffe2: fix prefix
Closes: https://bugs.gentoo.org/948897 Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/caffe2: wrong pocketfft path
Closes: https://bugs.gentoo.org/951726 Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv dev-cpp/gemmlowp to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/caffe2: enable mem efficient attention via use
Closes: https://bugs.gentoo.org/947932 Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/caffe2: depends on libfmt subslot
Closes: https://bugs.gentoo.org/950700 Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv dev-libs/oneDNN to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv dev-libs/FP16 to sci-ml
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv dev-libs/FBGEMM to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/XNNPACK to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/tensorpipe to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
*/*: mv sci-libs/onnx to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/NNPACK to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/kineto to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: move sci-libs/ideep to sci-ml/ideep
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Alfredo Tupone · gentoo
sci-ml/*: mv sci-libs/gloo to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
sci-ml/*: mc sci-libs/foxi to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org> - Repository mirror & CI · gentoo
Merge updates from master - Alfredo Tupone · gentoo
*/*: mv sci-libs/caffe2 to sci-ml/
Signed-off-by: Alfredo Tupone <tupone@gentoo.org>