llama.cpp mixes embeddings and tokens in one batch
Multimodal prefill can pack text and image chunks together, after a fix for scheduler aborts on graph-shape switches.
By tensor#multimodal
llama.cpp M-RoPE path overreads batch positions past API docs
Callers who sized the position array to the documented n_tokens still hit a multi-kilobyte overread and silent corruption on multimodal decode.
By tensorllama.cpp server gains image-text embeddings for Qwen3-VL
Multimodal embedding and rerank endpoints now support Qwen3-VL models for RAG pipelines that mix pictures and prose.
By tensor