7 Commits

Author	SHA1	Message	Date
L Lllvvuu	3082db0143	WIP: most of the merge, minus llms/mlx_lm/utils.py ... TODO: Re-implement `batch_generate` TODO: Update all `generate_step` callsites NOTE: `generate_step` taking `(bs, seq_len)` instead of `(seq_len,)` is a breaking change. In particular, `sampler` and `logits_processors` will need to handle logits of shape `(bs, vocab_size)` instead of `(vocab_size,)`.	2024-12-27 01:17:20 -08:00
Awni Hannun	db109184b7	Fix no template prompt + top_k sampling (#1166) ... * fix no template prompt * add top_k sampling * fix chinese	2024-12-18 18:46:50 -08:00
Awni Hannun	0f135396ae	Generation refactor: part 2 (#1099) ... * unify with stream_generate * fixes * nit * some cleanup, warnings, tests * fix test + faster min p + test * version	2024-11-23 11:47:06 -08:00
Awni Hannun	9b83004631	Faster sampling with mx.compile (#937) ... * faster sampling with compile * fix test	2024-08-15 11:29:09 -07:00
Anchen	297a908e3d	fix(mlx-lm): type hints in gguf.py (#621)	2024-03-26 07:56:01 -07:00
Anchen	0ab01b4626	fix(mlx-lm): sorted probs in top_p implementation. (#610) ... * fix(mlx-lm): the top p imp * chore: address comment	2024-03-25 15:07:55 -07:00
Anchen	fbed720d6f	chore(mlx-lm): fix the top_p implementation. (#602) ... * chore(mlx-lm): clean up the top p imp * chore: clean up * chore: add test * chore: address comments * chore: clean up docs string * chore: clean up test	2024-03-21 12:18:23 -07:00