112 Commits

Author	SHA1	Message	Date
George Hotz	15e0b56e39	compile works (#688) ... * compile works * runtimes * line count * fix custom, to tg dtype * meh, that's fine with lazy import	2023-03-12 11:01:25 -07:00
George Hotz	046b3952c3	get_state_dict	2023-03-11 23:46:53 -08:00
George Hotz	803b0aef28	track memory for numpy/torch	2023-03-11 20:39:10 -08:00
George Hotz	61071f881a	fix bug, and add unit test to catch failure	2023-03-11 16:57:25 -08:00
George Hotz	3ec457248c	failing llama test	2023-03-11 16:28:10 -08:00
George Hotz	8aa63847c7	llama: up max tokens to 1000	2023-03-11 13:39:33 -08:00
George Hotz	5ea44cefcc	llama: add lexie personality	2023-03-11 10:23:33 -08:00
George Hotz	c908f911a7	llama defaults to metal on osx	2023-03-11 09:30:13 -08:00
George Hotz	5e1380df6a	profiling llama + cache is_contiguous	2023-03-11 08:23:21 -08:00
George Hotz	f3ac52aee8	Mypyc (#680) ... * building shapetracker * default ENABLE_METHOD_CACHE * symbolic compiles * improve types * tensor compiles * oops, that's a bug * best of both worlds * find legit typing bugs * pad2d can take list or tuple * sub 200ms when compiled	2023-03-11 07:33:30 -08:00
George Hotz	b1206bcb18	third try at torch loading (#677) ... * third try at torch loading * numpy fixed * fix enet compile * load_single_weight supports empty weights * oops, CPU wasn't the default * so many bugs	2023-03-10 19:11:29 -08:00
George Hotz	4780f9a6df	llama runs (slowly) in master	2023-03-10 17:36:51 -08:00