llama.cpp
eef59a76 - llama: add llm_graph_input_mtp (#23643)

Commit
61 days ago
llama: add llm_graph_input_mtp (#23643) * llama: add llm_graph_input_mtp * rename input_mtp -> input_token_embd * add TODO about mtmd embedding * cont : clean-up --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Author
Parents
Loading