llama.cpp b11009

TP: fix split state and granularity for fused QKV gemma4, qwen35 (#28965)

• model: calculate split states for attn_qkv from n_head * n_embd_head_k

required for gemma4 with --fuse-qkv, where n_embd is 5376 but Q is 8192.

• model: handle fused full attention layers for qwen35/qwen35moe

• model: add TODO: [TAG_SPLIT_QGATE_QWEN]

Website: -

Attestations: -

UI:

• UI