mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-03-17 16:44:07 +00:00
* graph : avoid branches between embedding and token inputs * models : make deepstack graphs (e.g. Qwen3 VL) have constant topology * ci : enable -DGGML_SCHED_NO_REALLOC=ON for server CI * cont : pad token embeddings to n_embd_inp