ggml-org/llama.cpp b11240

on GitHub

server : support typed content (vision/audio/video) input for /v1/embeddings endpoint (#29556)

• server : support multimodal input for /v1/embeddings (Qwen3-VL-Embedding)

Accept the OpenAI-style wrapped content array format for multimodal
embedding requests. Each {"content": [...]} object is one input that
produces one embedding; text parts are concatenated and image_url parts
are decoded via handle_media then spliced with process_mtmd_prompt.

The legacy formats (plain string, token arrays, mixed arrays, and the
{prompt_string, multimodal_data} object) continue to work unchanged via
tokenize_input_prompts. Bare content arrays (the unwrapped shape) are
rejected with a migration message.

Also disables KV prefix reuse for stateless embedding/rerank tasks so
that repeated inputs do not incorrectly share cached KV across requests.

Assisted-by: Opencode Qwen3.8 27B

• clean up comments and docs

• refactor

• add tests

• support video and audio inp

Co-authored-by: timothywang21 timothywang21@users.noreply.github.com
Co-authored-by: Xuan Son Nguyen son@huggingface.co