5 Commits

Author	SHA1	Message	Date
Anchen	561dcf5643	Add support for deepseek coder v2 lite (#882) ... * feat: add support for deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct * fix softmax + some cleanup * more nits * fix rope * fix original_max_position_embeddings in rope * fix original_max_position_embeddings in rope config * add group greedy --------- Co-authored-by: Awni Hannun <awni@apple.com>	2024-07-17 07:23:28 -07:00
Prince Canuma	b044ce2acf	Add support for ibm granite (#758) ... * add support for granite 3-8B config * add gpt_bigcode * add positional embedding condition. * add support for granite 3-8B config * add gpt_bigcode * add positional embedding condition. * remove unused function * rebase fix * move position emebedding to mask creation * add to tuner and format * add support for granite 3-8B config * add gpt_bigcode * add positional embedding condition. * add support for granite 3-8B config * add gpt_bigcode * add positional embedding condition. * rebase fix * move position emebedding to mask creation * add to tuner and format * refactor mask * remove dropout layers	2024-05-21 20:16:31 -07:00
Awni Hannun	69181e0058	Support non incremental kv cache growth (#766)	2024-05-15 12:56:24 -07:00
Awni Hannun	ee60e2a9d5	Kv cache (#643) ... * in place kv_cache * fix * fix kv cache size * partially fix kv cache dtype * step kv cache * multiple of step size * more teests + kv cache * more kv cache * udpate all models to use kv cache	2024-05-08 08:18:13 -07:00
Awni Hannun	c6440416a2	Mlx llm package (#301) ... * fix converter * add recursive files * remove gitignore * remove gitignore * add packages properly * read me update * remove dup readme * relative * fix convert * fix community name * fix url * version	2024-01-12 10:25:56 -08:00