Models & Labs
Hugging Face Releases Ettin Reranker Models
Hugging Face Bloghigh confidence
Why it matters
- →Enhances search accuracy by reordering retrieved documents with high precision.
- →Supports long-context processing, accommodating up to 8,192 tokens.
- →Offers significant speed improvements, making it practical for real-world applications.
Hugging Face has introduced six new Sentence Transformers CrossEncoder rerankers, built on Ettin ModernBERT encoders. These models, ranging from 17 million to 1 billion parameters, are designed to improve search accuracy by reordering retrieved documents. They support long-context processing with up to 8,192 tokens and offer significant speed improvements. This release provides developers with advanced tools to enhance AI-driven search systems.
Read originalMore in Models & Labs
Models & Labsmodels
llama.cpp b10955 release addresses heap corruption
The latest release of llama.cpp, b10955, tackles a critical issue of heap corruption by disabling the ggml-cpu precompiled header and fixing CACHE_LINE_SIZE ambiguity. This update ensures consistent CACHE_LINE_SIZE values across C++ kernels and C work-buffer sizing code, preventing heap-buffer-overflow and subsequent crashes. By restoring the natural include order and removing the std::hardware_destructive_interference_size branch, the update makes the value deterministic and include-order independent. This release is a technical fix that stabilizes the runtime environment for developers using llama.cpp.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10956 release enhances SYCL backend
The latest llama.cpp release, b10956, introduces significant improvements to the SYCL backend, particularly for handling large k values in TOP_K operations. By implementing a radix select method, the update allows for efficient GPU-resident processing, avoiding previous limitations that forced operations to fall back to the CPU. This change enhances performance, especially in scenarios requiring large k values, such as qwen4exp's sparse-attention indexer. The update ensures that operations are more efficient and scalable, providing a notable boost in processing speed without regressing any measured shapes.