graph : create V as a view of K in the k_iswa build_attn (#27392)
build_attn with the llm_graph_input_attn_k_iswa input was using the cached K tensor itself as V. Create V as a view of K (the first v_cur->ne[0] elements of each row), like the other K-only build_attn overloads. The deepseek4 MTP call site now passes the kv tensor as v_cur. Assisted-by: pi:llama.cpp/Qwen3.8-27B
G
Georgi Gerganov committed
929d47a39163d67a2808413eaf8916097c4bb53c
Parent: f466cfa
Committed by GitHub <noreply@github.com>
on 8/20/2026, 7:00:35 AM