llama.cpp
c061df19 - Qwen4Exp: add MTP (#29761)

Commit
33 days ago
Qwen4Exp: add MTP (#29761) * Qwen4Exp: add MTP * remove has_state member, check via ctx_bufs being non-empty * consistent naming + less verbose comments * cont : clean-up recurrent memory * cont : clean-up comments --------- Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Author
Parents
Loading