llama.cpp

4f31296a - test-llama-archs : toggle causal_attn to catch graph shape changes (#29724)

test-llama-archs : toggle causal_attn to catch graph shape changes (#29724) After the device decode, flip causal_attn off, decode n_ubatch/2 then n_ubatch tokens. Both have the same node count, so a shape that depends on the flag makes the second reallocate at an unchanged graph size, which aborts under GGML_SCHED_NO_REALLOC. Skipped for the encode archs.