Samuel Oliveira Alves 28fbe34ce9 Dflash 2 speculative decoding (#2345) ... * Add DFlash2 speculative decoding support * Fix DFlash2 requantized output selection * Fix legacy DFlash output row contract * return llm_build_norm to apply also for dflash 2 * Fix DFlash2 GGUF conversion * capture dflash states in any type * remove duplicated layer_rows_raw		2026-08-26 17:09:34 +02:00
..
llama.h	Dflash 2 speculative decoding (#2345)	2026-08-26 17:09:34 +02:00