Improve `cvector-generator`

• Fix random direction of vector produced by PCA method https://github.com/ggerganov/llama.cpp/pull/8069#issuecomment-2185328171 (cc @jukofyork)
• Performance: Using batch and multi-sequences (for llama_decode)
• Performance: Allow using GPU (need to test, because some backends don't support certain ops)
• Add SVD and UMAP
• Add tests if possible

Ref: https://github.com/ggerganov/llama.cpp/pull/7514

Note: I'm writing this for tracking, but people are free to do PRs if you have any ideas to share. I'm planning to do some of the tasks in August 2024.