Coding Tools
llama.cpp b11886 adds Qwen merge and ROCm 10
llama.cpp Releaseshigh confidence
Why it matters
- →Qwen tensor merging resolves conversion errors for users running newer Qwen models locally.
- →ROCm 10.0 support provides a modern alternative to CUDA for AMD GPU owners.
- →Snapdragon builds indicate expanding support for on-device AI inference on mobile hardware.
llama.cpp has released version b11886, introducing support for Qwen tensor merging during conversion to improve compatibility with newer Qwen models. The update adds binaries for ROCm 10.0 and CUDA 13.4 across Linux and Windows platforms, expanding hardware support for AMD and NVIDIA GPUs respectively. Additionally, the release includes builds for Snapdragon processors on Linux and Android, reflecting growing interest in mobile AI inference. KleidiAI acceleration on Apple Silicon is currently disabled in this build.
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 b11040 release with CUDA 13 and ROCm 10
llama.cpp Releases · September 19, 2026 · Same story
- 2llama.cpp b11094 adds CUDA 13 and ROCm 10 builds
llama.cpp Releases · September 22, 2026 · Same story
More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12022 adds ROCm 10 and Snapdragon support
This release quietly cements llama.cpp as the universal inference runtime by finally bringing ROCm 10.0 to Linux and Windows alongside CUDA 13.4, effectively closing the hardware gap for AMD users who were previously left behind. The inclusion of native Snapdragon support on Linux marks a significant step toward running local LLMs on ARM-based mobile chips without emulation overhead. While KleidiAI on Apple Silicon is disabled in this build, the broader expansion to diverse accelerators ensures that developers aren't locked into NVIDIA ecosystems anymore.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12023 fixes shared prefix bug
This release addresses a specific inference artifact where decision prefixes were incorrectly bleeding into output embeddings. By capping shared prefixes at the first output position, llama.cpp ensures that option tokens remain distinct for parent and child tasks. This is a targeted fix for multi-step reasoning or voting workflows rather than a performance boost. It stabilizes complex generation patterns without changing the underlying model architecture.
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.316: Subagents and Gateway Budgets
Anthropic is tightening control over Claude Code's autonomous behavior with new environment variables that let you disable 'ultrathink' or cap subagent effort levels. For teams, the introduction of pooled group budgets on the gateway allows shared monthly spending limits across members, a practical fix for enterprise cost management. The release also patches critical bugs where shell commands would hang or crash on exit, stabilizing the developer experience significantly.
Claude Code Releases
© The Verge AICoding Toolscoding
