Models & Labs
Google unveils TimesFM-3 for multivariate forecasting
Google Research Bloghigh confidence
Why it matters
- →TimesFM-3 enables accurate multivariate forecasting in a single pass, reducing latency and error accumulation.
- →It outperforms existing models on major benchmarks, setting a new standard for forecasting accuracy.
- →The model's zero-shot capabilities allow it to handle complex scenarios without task-specific fine-tuning.
Google Research has introduced TimesFM-3, a new time series foundation model designed for multivariate forecasting. TimesFM-3 builds on previous versions by enabling predictions of multiple coevolving time series in a single forward pass, enhancing accuracy without the need for fine-tuning. The model, with 330 million parameters, has been pre-trained on a dataset of over 1 trillion time points. It outperforms other models on benchmarks like Gift-Eval and FEV-Bench, setting a new standard in forecasting. TimesFM-3 is available on GitHub and Hugging Face, with BigQuery integration coming soon.
Read originalMore from Google Research Blog
More in Models & Labs
Models & Labsmodels
llama.cpp b10739 Release Enhances M2 Max Performance
The b10739 release of llama.cpp brings targeted performance improvements for Apple's M2 Max, with fa-vec tuning specifically designed for its 30 GPU cores. This update aims to boost efficiency in AI processing tasks, making the most of Apple's latest hardware capabilities. While the KleidiAI feature for Apple Silicon remains disabled, the release continues to support a wide array of systems, including macOS, Linux, and Windows. The inclusion of ROCm 7.14 and CUDA 12 and 13 DLLs further extends its reach. This update marks a significant enhancement in llama.cpp's ability to adapt to different hardware environments, offering developers improved performance and flexibility.
llama.cpp Releases
Models & Labsmodels
llama.cpp b10741 Release Enhances Model Loading
The b10741 release of llama.cpp brings a key improvement in the model loading process by adjusting the order of parameter loading, specifically loading hparams.n_layer_nextn before n_layer() calls. This change aims to streamline initialization and eliminate redundant operations, enhancing efficiency. While no new model architectures are introduced, the update supports a wide range of hardware configurations, including macOS, Linux, and Windows systems. With support for ROCm 7.14 and CUDA 13, developers can expect a more robust runtime environment. This release continues llama.cpp's focus on refining its operations, making it a more efficient tool for developers working with diverse hardware setups.