Coding Tools
llama.cpp b12023 fixes shared prefix bug
llama.cpp Releaseshigh confidence
Why it matters
- →Fixes a bug where shared prefixes corrupted output embeddings in multi-step tasks.
- →Stabilizes inference for workflows using decision trees or voting mechanisms.
- →Maintains broad hardware support including CUDA 13 and ROCm 10.0 binaries.
llama.cpp has released version b12023, addressing issue #30482 regarding shared decision prefixes in server-side inference. The update limits shared prefixes to the first required output position of parent and child tasks, preserving decision output embeddings when questions share option tokens. The release includes standard binaries for macOS, Linux, Windows, and Android across CPU, CUDA 12/13, ROCm 10.0, and Vulkan backends. KleidiAI 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 Update Fixes Reasoning Budget Handling
llama.cpp Releases · July 13, 2026 · Same story
- 2llama.cpp b11435 fixes data race in shared sequences
llama.cpp Releases · October 6, 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 b12024 adds Snapdragon and ROCm 10
This release quietly expands llama.cpp's hardware support to include Qualcomm Snapdragon devices with CPU, Adreno GPU, and Hexagon NPU acceleration. It also updates ROCm to version 10.0 for both Linux and Windows, keeping AMD users in step with the latest driver stack. CUDA builds now default to 13.4 libraries alongside 12.x options, reflecting the industry's gradual shift toward newer NVIDIA toolkits. While no new model architectures are introduced, the binary matrix grows significantly, ensuring local inference remains viable on a wider array of edge and server hardware.
llama.cpp Releases
Coding Toolscoding
llama.cpp b12027 adds CUDA 13 and Snapdragon support
This release quietly modernizes the local inference stack by adding native support for CUDA 13.4 alongside the existing CUDA 12 builds, ensuring compatibility with the latest NVIDIA driver ecosystems without forcing users to stay on older stacks. The inclusion of ROCm 10.0 and OpenVINO further solidifies llama.cpp as the universal runtime for heterogeneous hardware, while new binaries for Linux arm64 Snapdragon devices bring AI inference to mobile-class ARM silicon. Apple Silicon builds have reverted KleidiAI to disabled by default, a pragmatic choice that prioritizes stability over experimental performance gains for the average user. The result is a more future-proof binary set that removes friction for developers adopting next-generation GPUs and edge processors.
llama.cpp Releases
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
DIY Muse Gadget proves Meta's hardware is just a dev kit
Meta’s Muse Charm isn’t a finished product; it’s an invitation to hack. A non-coder used Claude Code to transform a $50 Waveshare ESP32-S3 dev board into a fully functional AI companion, adding ElevenLabs voice synthesis, custom Tamagotchi-style minigames, and remote camera controls that Meta’s official firmware lacks. This reveals a critical truth: the value of Meta’s new hardware ecosystem lies not in its out-of-the-box utility, but in its open-source API allowing anyone to rewrite the experience. The gap between Meta’s polished demo and the actual user reality is bridged entirely by third-party AI coding tools.
The Verge AI
© The AI Daily BriefCoding Toolswriting
Granola launches free dictation feature
Granola has released a new free dictation tool for users.
The AI Daily Brief