BLAST RADIUS

Open-weight & owned stack · Quantization efficiency

llama.cpp adds multimodal embeddings endpoint support

Sep 28, 2026, first seen via Training & inference tooling releases

llama.cpp b11240 added OpenAI-style vision, audio, and video inputs to its embeddings endpoint and disabled unsafe KV-prefix reuse.

Read the original at github.comOpens the publisher's site in a new tab

More in Open-weight & owned stack