llama.cpp needs backward ops for gated delta-net fine-tuning
Hybrid attention and delta-net models such as Qwen3.5 cannot run through llama_opt_epoch until several missing gradient rules land.
By tensor#qwen
llama.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