Coding Tools
llama.cpp b12175 fixes CI hangs, adds ROCm 10 and CUDA 13
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes CI hangs that were blocking reliable binary generation for self-hosted runners.
- →Adds native ROCm 10.0 support, improving AMD GPU compatibility for local inference.
- →Updates CUDA support to version 13, ensuring compatibility with the latest NVIDIA driver stacks.
llama.cpp version b12175 addresses critical CI stability issues and updates backend support for modern hardware stacks. The release fixes a threading concurrency bug in test-llama-context that caused hangs on self-hosted CPU runners, ensuring more reliable automated builds. Key technical additions include native support for ROCm 10.0 and CUDA 13 (up to 13.5) on Linux and Windows platforms. Apple Silicon builds now include KleidiAI optimizations, though this feature is disabled by default in the precompiled binaries. The update maintains broad compatibility across x64, arm64, and specialized architectures like openEuler.
Read originalThe story around this
Earlier coverage that leads up to this article, and what followed. Lines connect each piece to the closest one after it, converging here.
How we got here
- 1llama.cpp b11027 adds CUDA 13 and ROCm 10 builds
llama.cpp Releases · September 18, 2026 · Same story
- 2llama.cpp b11155 adds ROCm 10 and CUDA 13 support
llama.cpp Releases · September 24, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12173 adds OpenCL repeat ops
This release quietly patches a gap in llama.cpp's OpenCL backend by adding support for the 'repeat' operation across f16, i32, i16, and bf16 types. For users relying on AMD or Intel GPUs via OpenCL rather than Vulkan or ROCm, this means fewer fallbacks to slower CPU execution for models that use these tensor operations. It’s a targeted fix that improves stability and performance on non-NVIDIA hardware without changing the core inference engine. The update also includes standard binaries for CUDA 13 and ROCm 10.0, keeping the stack current with latest driver ecosystems.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12174 adds ROCm 10 and CUDA 13
This release quietly closes the hardware gap for non-NVIDIA users by adding default support for ROCm 10.0 on both Linux and Windows, allowing AMD GPU owners to run local models without complex configuration. It also brings CUDA 13.5 builds to Ubuntu and Windows, future-proofing the toolchain for newer NVIDIA architectures while maintaining backward compatibility with CUDA 12. Apple Silicon KleidiAI is disabled in this build, a notable regression for Mac users who rely on that specific optimization. The update solidifies llama.cpp's position as the most versatile inference runtime available, covering everything from Snapdragon NPUs to Intel Arc via SYCL.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12176 fixes C++ math compatibility
This release quietly patches a compilation failure on NetBSD by qualifying C math functions with std::, ensuring llama.cpp builds cleanly across stricter C++ environments. The change also corrects a subtle precision issue in test-quantize-fns.cpp where sqrtf was used with double accumulators, now switched to std::sqrt for better accuracy. While the behavioral difference is negligible for inference, this cleanup prevents future build breaks on non-standard Linux distributions and reinforces the project's commitment to portable, standards-compliant code.
llama.cpp Releases
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.319: MCP backgrounding and gateway controls
This release finally brings proper asynchronous handling to Model Context Protocol tasks, allowing Claude Code to offload long-running tool calls to the background instead of blocking the main thread. For enterprise users, the new pooled budget rules and JSON logging make the Claude apps gateway significantly more manageable for large teams. The update also tightens error reporting in auto mode, ensuring developers get clear reasons when actions are denied rather than silent failures. It’s a pragmatic patch that improves reliability for complex agent workflows.
Claude Code Releases
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Code Review API and UI updates
GitHub is finally exposing Copilot code review configuration to the REST and GraphQL APIs, closing a major gap for enterprise automation. Administrators can now programmatically control review effort, enablement, and custom instructions across organizations and repositories, moving beyond manual web interface tweaks. The update also refines the user experience with compact overviews, explicit attribution of AI sources like MCP servers, and better handling of bot-authored PRs. This shift makes Copilot Review a first-class citizen in CI/CD pipelines rather than just a UI feature.
GitHub Changelog
© GitHub ChangelogCoding Toolscoding
GitHub Copilot Dashboard Adds Chat and Agent Metrics
GitHub finally stops treating chat as a passive afterthought in its enterprise analytics. By adding Copilot Chat and the VS Code Agents window to the impact dashboard, the platform now tracks nine distinct experiences instead of just seven. The rebranding of 'Passive users' to 'Chat-first users' is a semantic correction that aligns metrics with actual developer behavior rather than arbitrary adoption thresholds. This gives engineering leaders a complete picture of how AI is actually being used across their codebases, closing the visibility gap between typing commands and writing code.
GitHub Changelog