Models & Labs
IBM releases Granite Time Series PatchTST-FM-r2 model
Hugging Face Bloghigh confidence
Why it matters
- →The model offers strong zero-shot forecasting capabilities, reducing the need for dataset-specific training.
- →Its architecture efficiently captures both long- and short-term temporal structures, enhancing forecasting accuracy.
- →The permissive licensing makes it accessible for commercial use, promoting wider adoption in enterprise settings.
IBM has unveiled the Granite Time Series PatchTST-FM-r2 model, a state-of-the-art time-series forecasting tool. This model, boasting approximately 385 million parameters, is designed for zero-shot forecasting, meaning it can generate predictions without prior training on specific datasets. It ranks highly on the GIFT-Eval benchmark, particularly among models with permissive licenses. The model's architecture incorporates conformer blocks, which improve its ability to capture both long- and short-term temporal patterns. Available under a dual open-source license, it provides transparency and flexibility for commercial applications.
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.