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
..
__init__.py	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
constants.py	Dflash 2 speculative decoding (#2345)	2026-08-26 17:09:34 +02:00
gguf.py	gguf-py: Refactor and allow reading/modifying existing GGUF files (#3981)	2023-11-11 08:04:50 +03:00
gguf_reader.py	Make gguf-py stuff work with numpy 2.0 (#991)	2025-11-20 10:20:55 +01:00
gguf_writer.py	Dflash 2 speculative decoding (#2345)	2026-08-26 17:09:34 +02:00
lazy.py	Merge mainline - Aug 12 2024 (#17)	2024-08-12 15:14:32 +02:00
metadata.py	Merge mainline - Aug 12 2024 (#17)	2024-08-12 15:14:32 +02:00
py.typed	convert : various script cleanups/fixes + merges and special token handling (#2842)	2023-08-30 11:25:50 +03:00
quants.py	convert_hf_to_gguf.py : conversion from hf weights to Q6_0 (#483)	2025-06-03 09:30:30 +03:00
tensor_mapping.py	Dflash 2 speculative decoding (#2345)	2026-08-26 17:09:34 +02:00
utility.py	Merge mainline llama.cpp (#3)	2024-07-27 07:55:01 +02:00
vocab.py	model: add Cohere2-MoE North Mini Code support (#1945)	2026-06-10 15:28:27 +02:00