mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-27 00:17:27 -05:00
Skip the nb[3] check when ne[3] == 1, the shader never reads it for a single stream. Cache views carry the full-buffer stride there, so the old check reduced to n_kv == kv_size and the path only engaged with the cache full.