Coding Tools
llama.cpp v12347 cleans up API and promotes speculative decoding
llama.cpp Releaseshigh confidence
Why it matters
- →Speculative decoding is now officially supported via stable APIs, reducing integration friction.
- →Deprecated warmup and defragmentation features are removed, requiring code updates from maintainers.
- →The library interface is cleaner, signaling a shift toward mature, production-ready speculative inference tools.
llama.cpp version 12347 focuses on API stabilization and cleanup. The release promotes the NextN speculative decoding API from the experimental `llama-ext.h` header to the stable `llama.h`, making draft model inference a first-class citizen in the library. Concurrently, deprecated functions like `llama_set_warmup` and the `--defrag-thold` command-line option have been removed to reduce technical debt. These changes require developers to update their codebases but provide a more robust foundation for building speculative decoding applications.
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 b10094 Release Enhances Speculative Type Inference
llama.cpp Releases · July 25, 2026 · Same story
- 2llama.cpp v0.7.0: MoE caching and speculative decoding advances
llama.cpp Releases · October 16, 2026 · Same story
Follow this story
Open the full story →More from llama.cpp Releases
Coding Toolscoding
llama.cpp b12336 fixes HunyuanVL crash
This release quietly patches a critical memory overflow in the mtmd module that caused crashes when loading HunyuanVL models. The issue stemmed from F64 position embeddings overflowing an F32 buffer, a subtle bug that broke multimodal inference for users relying on this specific architecture. By enforcing strict F32 requirements, llama.cpp stabilizes support for Tencent's vision-language model without adding new features or changing the core API. It’s a necessary maintenance update that keeps local multimodal workflows from breaking unexpectedly.
llama.cpp Releases
Models & Labsother
llama.cpp b12340 adds CUDA 13 and ROCm 10.0
This release quietly closes the hardware gap for local inference by adding default support for CUDA 13 and ROCm 10.0 across Linux and Windows. Users with newer NVIDIA GPUs or AMD accelerators no longer need to compile from source to get performance, while Apple Silicon builds now ship KleidiAI disabled by default, shifting the focus back to standard ARM optimizations. The inclusion of Snapdragon support for Linux and Android marks a significant step toward on-device AI beyond the x86/ARM desktop ecosystem. It is less about new features and more about ensuring llama.cpp remains the universal runtime for every available accelerator.
More in Coding Tools
Coding Toolscoding
Claude Code v2.1.323 adds experimental Code Mode and plugin safety
This release quietly introduces Code Mode, an opt-in feature where Claude writes JavaScript to call its own tools, marking a shift toward more autonomous agent-like behavior within the CLI. The update also hardens the plugin ecosystem by enforcing version ranges and adding strict TypeScript type checking for hooks, which should significantly reduce instability from third-party extensions. Beyond these features, the changelog is dominated by critical fixes for authentication drift in background sessions and memory leaks when handling large files, stabilizing the tool for heavy enterprise use.
Claude Code Releases
© GitHub ChangelogCoding Toolscoding