We are pleased to announce the release of version 0.3.1, now available for download. This patch release delivers focused improvements to both and modules. gains a new LapackSyev eigensolver for symmetric and Hermitian eigenvalue decomposition, VirtualStrided support for referencing dense matrix diagonals, and a comprehensive header restructuring that organizes all internal include paths into dedicated subdirectories. introduces dense object fill operations, extended cuSOLVER support, a new GridXD utility class for GPU kernel launch configuration, and stabilized SVD and GEEV implementations. Handler implementations have been moved from header-only to compiled translation units with explicit specializations, significantly reducing build times. Bug fixes address complex SVD correctness and complex_t arithmetic operators across both modules.

We are thrilled to announce the release of version 0.3.0, now available for download. This release brings substantial improvements across both and modules. Key enhancements to include expanded CSR matrix support with Pardiso integration, along with optimized template-based validation checks for enhanced compile-time performance. The module features major additions including complete eigenvalue decomposition (GEEV) capabilities, a sophisticated virtual expression system enabling lazy evaluation for GPU operations, and an extensive functional algebra API supporting inner products, outer products, and symmetric/Hermitian matrix operations. Additional improvements include enhanced sparse matrix operations with CSR and CSC format support, comprehensive cuBLAS handler enhancements, and numerous bug fixes across both modules. Complete documentation and updated API references are now available to help developers leverage these advanced computational capabilities.

We are excited to announce the official release of version 0.2.0, now available for download. This release introduces significant enhancements to , including comprehensive support for Compressed Sparse Row (CSR) matrix format, expanding the library's sparse matrix capabilities. Additionally, version 0.2.0 marks the initial release of , our GPU-accelerated library featuring vector and matrix handling on GPU architectures, along with a basic linear solver utilizing LU decomposition. Developers can now access the complete documentation and updated API references to begin integrating these high-performance computational tools into their workflows.

We are excited to announce the official release of version 0.1.0, now available for download. This milestone release marks the transition of the suite into its first public stable development phase. In addition to critical performance optimizations for C++ linear algebra, this version serves as the foundational dependency for our upcoming GPU-accelerated library, . Developers can now access the full documentation and updated API references to begin integrating these high-performance tools into their computational workflows.