Merge pull request #831 from admiralakber/chore/update-llama-cpp-b6482

Update llama.cpp to b6482 (3d4053f)

Merge pull request #820 from emilnorsker/main

Expose separator token

Merge pull request #819 from fellhorn/dennis/mtmd-improvements

Multimodality improvements

Merge pull request #815 from mediest/feat/expose-ggml-kv-types

Add KV cache type (K/V) configuration to LlamaContextParams

Merge pull request #790 from fellhorn/dennis/feat/multi-modal

Multimodality support

Merge pull request #802 from tmetsch/main

fix: create fresh batch for each line in embedding example

Merge pull request #795 from utilityai/dependabot/cargo/clap-4.5.42

chore(deps): bump clap from 4.5.41 to 4.5.42

Merge pull request #797 from caer/caer-gpt-oss-update

Update `llama.cpp` to latest version supporting `gpt-oss`

Merge pull request #792 from Kakadus/bindgen-update

Bump bindgen from 0.69.5 to 0.72.0

Merge pull request #786 from fellhorn/dep/update_llama_cpp_b6002

Bump llama.cpp to b6002