Kawrakow f5e5753c32 Fix Qwen35 mtp warmup (#1987) ... * Use hidden state from prev token from qwen mtp * Fix Qwen35 MTP warmup * Cleanup + remove unnecessary crippling performance by not using accept to sample draft token * Provide API to gtet the model arch string --------- Co-authored-by: SamuelOliveirads <samueloliveira32df@gmail.com>		2026-06-18 09:03:40 +02:00
..
llama.h	Fix Qwen35 mtp warmup (#1987)	2026-06-18 09:03:40 +02:00