Models & Labs
Hugging Face Launches olmo-eval for LLM Development
Hugging Face Bloghigh confidence
Why it matters
- →olmo-eval enhances the flexibility and speed of LLM development by simplifying the evaluation process.
- →It supports agentic and multi-turn evaluations, offering a more comprehensive analysis of model performance.
- →The tool's modularity allows for easy integration and reuse of components, streamlining the development workflow.
Hugging Face has launched olmo-eval, an evaluation workbench aimed at improving the development loop for large language models (LLMs). This tool builds on the Open Language Model Evaluation Standard (OLMES) and offers greater flexibility in defining and running benchmarks. Unlike other tools, olmo-eval supports agentic and multi-turn evaluations, making it easier to assess real-world model performance. It allows developers to quickly implement new evaluations and analyze results, facilitating faster iterations in model development.
Read originalMore from Hugging Face Blog
More in Models & Labs
Models & Labsmodels
Llama.cpp adds GLM-5.2 speculative decoding support
Llama.cpp's latest update introduces speculative decoding support for GLM-5.2, enhancing its capabilities with NextN/MTP features. This addition allows for more efficient tensor loading and context management, particularly benefiting models using the GLM_DSA architecture. The update also includes options for exporting models with or without the MTP feature, providing flexibility for developers. This release marks a step forward in optimizing model performance and adaptability, especially for those leveraging the GLM-5.2 framework.
llama.cpp Releases
Models & Labsmodels
Llama.cpp b10178 Release Adds Trace Logging
The b10178 release of llama.cpp enhances its server capabilities by adding trace logging for slot similarity checking, offering developers detailed insights into prompt cache slot selection processes. This update includes specifics on skip reasons and similarity calculations, which can aid in performance optimization. While no new model architectures are introduced, the release continues to support a wide array of platforms, such as macOS with KleidiAI, Ubuntu with ROCm 7.2, and Windows with CUDA 12 and 13. This makes llama.cpp a more versatile tool for developers working on different systems, reinforcing its position as a comprehensive inference runtime.
