Coding Tools
llama.cpp adds Carbon-14B DNA tokenizer support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables local inference of Carbon-14B genomic models without custom conversion scripts.
- →Fixes tokenization for older Carbon model variants (500M/3B/8B) that previously lacked proper support.
- →Expands llama.cpp's utility in specialized scientific domains like bioinformatics.
The llama.cpp project has merged support for the Carbon-14B HybridDNA tokenizer, enabling local inference of genomic language models. The update addresses specific tokenization quirks, including auto-tagging untagged DNA sequences and correcting special token handling for older Carbon model sizes (500M/3B/8B). This release allows developers to run these specialized bio-AI tools on various hardware backends, including CUDA, ROCm, and Apple Silicon, without manual tokenizer adjustments.
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 b10593 Release Fixes and Enhancements
llama.cpp Releases · August 24, 2026 · Related
- 2llama.cpp b10970 Release Expands Platform Support
llama.cpp Releases · September 15, 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
