mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-09-17 20:31:47 +02:00
* llama: avoid copying logits during prompt decode in MTP * review: update comment * llama-graph: call set_output for t_h_pre_norm
* llama: avoid copying logits during prompt decode in MTP * review: update comment * llama-graph: call set_output for t_h_pre_norm