b9605
ggml-org/llama.cppb9605Jun 12, 2026by github-actions[bot]same day as b9604
What changed since b9604
Adds CUDA support for tensor concatenation and fixes Metal CI issues.
New features
- Support for concatenating tensors of scalar types in the CUDA backend
Improvements
- Resolved Metal CI issue during update
Upgrade notes
No configuration changes required. Simply download the updated binaries for your platform.
Analyzed Oct 22, 2026
Upgrading?
Release notes summary
Adds support for concatenating tensors of scalar types in the CUDA backend. Also fixes a Metal CI issue during the update.
Key Highlights
- Support concat for scalar types at cuda backend
- Update concat.cu
- Fix metal ci issue
Release Notes (excerpt)
<details open> ggml: support concat for scalar types at cuda backend (#24011) * cuda: support concat for scalar types * Update concat.cu * fix metal ci issue </details> **macOS/iOS:** - macOS Apple Silicon (arm64) - macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED - macOS Intel (x64) - iOS XCFramework **Linux:** - Ubuntu x64 (CPU) - Ubuntu arm64 (CPU) - Ubuntu s390x (CPU) - Ubuntu x64 (Vulkan) - Ubuntu arm64 (Vulkan) - Ubuntu x64 (ROCm 7.2) - Ubuntu x64 (OpenVINO)…
Published by ggml-org on GitHub.
Read the full release notesRelated Repositories
:electron: Build cross-platform desktop apps with JavaScript, HTML, and CSS
Godot Engine – Multi-platform 2D and 3D game engine
ClickHouse® is a real-time analytics database management system
Self-hosted game stream host for Moonlight.
DuckDB is a high-performance analytical database system