Topic: sparse

The ggml/llama.cpp project released version b11062, which includes a CUDA update enabling sparse FA for qwen4 (#28770). This update is significant as it enhances the performance and efficiency of the model on specific hardware.

Linkup Research has unveiled SPARSEUP, an open-source sparse embedding model with 149 million parameters that outperforms other models in its class on the BEIR-13 benchmark, highlighting advancements in efficient large-scale language modeling.

marktechpost.com↗