Coding Tools
llama.cpp adds ModernBERT reranker support
llama.cpp Releaseshigh confidence
Why it matters
- →Enables native semantic reranking in local RAG pipelines using ModernBERT.
- →Eliminates dependency on external APIs for high-quality document re-ranking.
- →Simplifies local AI stack by integrating pooling logic directly into llama.cpp.
llama.cpp has released an update adding support for classifier_pooling in ModernBERT rerankers, enabling native semantic reranking within the library. The implementation reads pooling types from model configurations and supports 'cls' and 'mean' methods, with a fallback to mean for unspecified cases. This enhancement allows developers to integrate high-performance reranking models directly into local retrieval-augmented generation (RAG) pipelines without relying on external services or complex setups.
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 enables chunked prefill for causal rerankers
llama.cpp Releases · September 28, 2026 · Same story
What happened next
- 2llama.cpp UI adds offline context filtering and favorites
llama.cpp Releases · October 10, 2026 · Related
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