Topic: contiguous

The ggml/llama.cpp project released a new version (b11060) that includes fixes to make time-step projection input contiguous and skip unnecessary contiguous copies after normalization, aimed at improving efficiency. These updates are significant for enhancing the performance of the model without compromising accuracy.

The ggml/llama.cpp project released version b10991, which includes the addition of a missing contiguous fast-path and hvx_copy_uu for each run. This update is significant as it enhances performance on specific hardware configurations.