63 packages
| Package ▲ | Version | Maintainers | # | Teams | Deps | Used by | Used by (transitive) | Status |
|---|---|---|---|---|---|---|---|---|
oneAPI Deep Neural Network Library (oneDNN) |
2.7.5 |
4 | 3 | 1 | 2 | team-only | ||
OpenCL Conformance Test Suite |
2025-08-21-00 |
4 | 9 | 0 | 0 | team-only | ||
AI Tensor Engine for ROCm |
0.1.11.post1 |
5 | 40 | 0 | 0 | maintained | ||
System management interface for AMD GPUs supported by ROCm |
7.2.3 |
5 | 7 | 0 | 0 | maintained | ||
AI Tensor Engine for ROCm |
0.1.11.post1 |
5 | 40 | 0 | 0 | maintained | ||
System management interface for AMD GPUs supported by ROCm |
7.2.3 |
5 | 7 | 1 | 1 | maintained | ||
ROCm Ahead of Time (AOT) Triton Math Library |
0.12b |
4 | 20 | 2 | 3 | team-only | ||
AQLPROFILE library for AMD HSA runtime API extension support |
7.2.3 |
4 | 4 | 2 | 3 | team-only | ||
Pytorch inductor backend which uses composable_kernel universal GEMM implementations |
7.2.3 |
4 | 18 | 0 | 0 | team-only | ||
AMD Common Language Runtime for hipamd, opencl, and rocclr |
7.2.3 |
5 | 24 | 48 | 49 | maintained | ||
Performance portable programming model for machine learning tensor operators |
7.2.3 |
4 | 11 | 1 | 5 | team-only | ||
Performance portable programming model for machine learning tensor operators |
7.2.3 |
4 | 11 | 0 | 0 | team-only broken | ||
C++ library for half precision floating point arithmetics |
7.2.3 |
4 | 4 | 6 | 8 | team-only | ||
C++ Heterogeneous-Compute Interface for Portability |
7.2.3 |
5 | 2 | 1 | 50 | maintained | ||
ROCm BLAS marshalling library |
7.2.3 |
4 | 11 | 11 | 14 | team-only | ||
Common files shared by hipBLAS and hipBLASLt |
7.2.3 |
4 | 4 | 8 | 23 | team-only | ||
Library that provides general matrix-matrix operations with a flexible API |
7.2.3 |
4 | 23 | 7 | 22 | team-only | ||
Compiler driver utility that calls clang or nvcc |
22.0.0-rocm |
5 | 6 | 3 | 50 | maintained | ||
Thin wrapper library on top of rocPRIM or CUB |
7.2.3 |
4 | 6 | 2 | 2 | team-only | ||
FFT marshalling library |
7.2.3 |
4 | 6 | 4 | 4 | team-only | ||
Fortran interfaces for ROCm libraries |
7.2.3 |
4 | 5 | 0 | 0 | team-only | ||
Convert CUDA to Portable C++ Code |
7.2.3 |
4 | 9 | 3 | 9 | team-only | ||
HIP wrapper for rocRAND and cuRAND |
7.2.3 |
4 | 6 | 2 | 6 | team-only | ||
Ray tracing library for HIP |
3.0.3.a1525e7 |
5 | 5 | 0 | 0 | maintained | ||
ROCm SOLVER marshalling library |
7.2.3 |
4 | 10 | 3 | 3 | team-only | ||
ROCm SPARSE marshalling library |
7.2.3 |
4 | 7 | 5 | 7 | team-only | ||
ROCm hipSPARSELt - a SPARSE marshalling library |
7.2.3 |
4 | 17 | 0 | 0 | team-only | ||
Platform runtime for ROCm |
7.2.3 |
5 | 13 | 10 | 56 | maintained | ||
AMD's graph optimization engine |
7.2.3 |
4 | 24 | 1 | 1 | team-only | ||
Machine intelligence library for ROCm |
7.2.3 |
4 | 20 | 4 | 4 | team-only | ||
Set of comprehensive computer vision and machine intelligence libraries, utilities, and applications |
7.2.3 |
4 | 21 | 0 | 0 | team-only | ||
Set of comprehensive computer vision and machine intelligence libraries, utilities, and applications |
7.2.3 |
4 | 17 | 0 | 0 | team-only | ||
ROCm communication collectives library |
7.2.3 |
4 | 17 | 1 | 1 | team-only | ||
Simplifies administration and addresses infrastructure challenges in cluster and datacenter environments |
7.2.3 |
4 | 14 | 0 | 0 | team-only | ||
Iterative sparse solvers for ROCm |
7.2.3 |
4 | 12 | 0 | 0 | team-only | ||
BLAS implementation for ROCm platform |
7.2.3 |
4 | 27 | 16 | 21 | team-only | ||
Debugger support for control of execution and inspection state of AMD's GPU architectures |
7.2.3 |
4 | 10 | 2 | 2 | team-only | ||
FFT implementation for ROCm |
7.2.3 |
4 | 8 | 1 | 5 | team-only | ||
ROCm source-level debugger for Linux, based on GDB |
7.2.3 |
4 | 18 | 0 | 0 | team-only | ||
Bandwidth test for AMD GPUs supported by ROCm |
6.3.3 |
5 | 4 | 0 | 0 | maintained | ||
CMake modules for common build tasks for the ROCm stack |
7.2.3 |
4 | 4 | 36 | 56 | team-only | ||
APIs for compiling and inspecting AMDGPU code objects |
22.0.0-rocm |
5 | 11 | 5 | 53 | maintained | ||
Utility for getting the ROCm release version |
7.2.3 |
4 | 3 | 2 | 57 | team-only | ||
Set of AMD-specific device-side language runtime libraries |
22.0.0-rocm |
5 | 10 | 7 | 58 | maintained | ||
ROCm Documentation Python package for ReadTheDocs build standardization |
1.34.0 |
4 | 31 | 0 | 0 | team-only | ||
System management interface for AMD GPUs supported by ROCm |
7.2.3 |
5 | 6 | 8 | 27 | maintained | ||
ROCm Application for Reporting System Info |
7.2.3 |
5 | 8 | 3 | 50 | maintained | ||
MLIR-based convolution and GEMM kernel generator |
7.2.3 |
4 | 15 | 2 | 5 | team-only | ||
ROCm parallel primitives |
7.2.3 |
4 | 5 | 9 | 23 | team-only | ||
Library for decoding ROCm thread trace data |
0.1.7 |
4 | 8 | 1 | 1 | team-only | ||
Profiling with perf-counters and derived metrics |
7.2.3 |
4 | 20 | 1 | 2 | team-only | ||
Profiling with perf-counters and derived metrics |
7.2.3 |
4 | 15 | 4 | 57 | team-only | ||
Library that provides some debugging functionality for ROCr |
7.2.3 |
4 | 7 | 0 | 0 | team-only | ||
Generate pseudo-random and quasi-random numbers |
7.2.3 |
4 | 5 | 3 | 11 | team-only | ||
The ROCm OpenSHMEM (rocSHMEM) runtime |
7.2.3 |
4 | 7 | 0 | 0 | team-only | ||
ROCm LAPACK implementation |
7.2.3 |
4 | 9 | 7 | 16 | team-only | ||
ROCm SPARSE implementation |
7.2.3 |
4 | 8 | 9 | 20 | team-only | ||
ROCm parallel algorithm library |
7.2.3 |
4 | 6 | 3 | 3 | team-only | ||
Tracer callback/activity library |
7.2.3 |
4 | 9 | 3 | 24 | team-only | ||
Mixed precision matrix multiplication and accumulation |
7.2.3 |
4 | 6 | 0 | 0 | team-only | ||
Comprehensive high-performance computer vision library for AMD processors |
7.2.3 |
4 | 8 | 1 | 1 | team-only | ||
Comprehensive high-performance computer vision library for AMD processors |
7.2.3 |
4 | 8 | 1 | 1 | team-only | ||
GEMMs and tensor contractions |
7.2.3 |
4 | 23 | 1 | 22 | team-only |