46 commits

Author	SHA1	Message	Date
niansa	90e54d66d0	Removed cosched support	2024-03-25 01:18:37 +01:00
niansa	ef5df1dc31	Updated llama.cpp-mainline	2023-11-09 12:51:53 +01:00
niansa	fc5e4f5aa1	Updated llama.cpp-mainline	2023-10-04 22:13:48 +02:00
niansa	215db6b9b7	Fully implemented grammar sampling	2023-09-05 10:22:42 +02:00
niansa	79cf49faae	Implemented grammar sampling and zero-temperature sampling	2023-08-31 19:37:33 +02:00
niansa	3a953ed13a	Convert tokens to text correctly in llama	2023-08-31 18:23:55 +02:00
niansa	907cea7f9d	Fixed exception if pre_tick is nullptr	2023-08-31 18:07:42 +02:00
niansa	7cd3899dd0	Check for correct magic value in llama	2023-08-31 17:57:56 +02:00
niansa	5d818e31aa	Call llama_backend_init()/llama_backend_free()	2023-08-31 16:56:10 +02:00
niansa	e3d52c42b7	Updated llama-mainline and deleted old llama versions	2023-08-31 16:52:38 +02:00
niansa	d8f4efb0c9	Cut off ending from run() result properly	2023-06-25 01:20:56 +02:00
niansa	01b0d059ed	Added pre_tick	2023-06-15 18:14:09 +02:00
niansa	0199db02b7	Added GPU support	2023-06-10 00:49:21 +02:00
niansa	94953cd174	Improve some error handling macros	2023-06-09 23:53:01 +02:00
niansa	53a4623aef	Added mirostat support	2023-05-26 00:43:07 +02:00
niansa	fe850337df	Pass context to llama_sample_repetition_penalty	2023-05-21 15:40:49 +02:00
niansa	85eb2047cb	Improved llama.cpp version naming scheme	2023-05-20 16:53:03 +02:00
niansa	9a3952597a	Another abort fix	2023-05-20 03:09:25 +02:00
niansa	30a0a77cb2	Fixed an abort()	2023-05-20 02:53:32 +02:00
niansa	5feca59be7	Fixed linebreaks and support latest llama.cpp	2023-05-20 02:25:46 +02:00
niansa	a608135bf7	Removed new llama sampling stub	2023-05-19 16:39:09 +02:00
niansa	ad1e8a3368	Completed mainline llama implementation	2023-05-19 16:35:55 +02:00
niansa	4974338e41	Fixup step #2	2023-05-19 16:18:26 +02:00
niansa	9bf70e3f5d	Renamed llama-mainline to llama_old	2023-05-19 15:57:17 +02:00
niansa	abbb35c6a9	Minor improvements on EOS handling	2023-05-17 10:51:20 +02:00
niansa	4ec47699f0	Repeat penalty fixes	2023-05-17 08:44:25 +02:00
niansa	60fe6b9c55	Load implemenations as shared objects	2023-05-16 19:10:05 +00:00
niansa	59a6a8b1d1	Check for errors during llama evaluation properly	2023-05-11 18:46:41 +02:00
niansa	087fe1396b	Fixed all other known compilation issues	2023-05-10 21:50:37 +02:00
niansa	b61c751d33	Reverted last commit. but fixed invalid ssize_t typedef on msvc	2023-05-10 16:39:44 +02:00
niansa	bdb87534e8	Eliminate use of ssize_t	2023-05-10 16:37:43 +02:00
niansa	6968f3459a	Made last commit more beautiful	2023-05-09 22:25:04 +02:00
niansa	a43c5e64ce	Fixed compilation error with exceptions enabled	2023-05-09 22:23:34 +02:00
niansa	5e666d83db	Actually implemented error return values	2023-05-09 22:20:01 +02:00
niansa	0d5cba0530	Added LM_NOEXCEPT cmake option	2023-05-09 21:33:49 +02:00
niansa	7076f863d4	Check for task termination	2023-05-05 19:02:28 +02:00
niansa	5a57db5e75	Added CoSched support	2023-05-04 15:22:32 +02:00
niansa	d236e36d26	Implemented proper scrolling	2023-04-28 18:04:07 +02:00
niansa	493186509a	Renamed function and updated Python bindings	2023-04-27 09:48:44 +02:00
niansa	ca4ad5f096	Added context window scrolling with top bar	2023-04-27 09:45:37 +02:00
niansa	219186f4b6	Take const string reference instead of string view in append()	2023-04-27 09:31:22 +02:00
niansa	4e74517bb5	Changed parameter types to some that make more sense	2023-04-27 09:27:09 +02:00
niansa	0661b2e33d	Updated for latest llama.cpp and working gpt-j implementation	2023-04-27 08:21:02 +02:00
niansa	566f8227fd	Should be functional now	2023-04-27 08:00:08 +02:00
niansa	316e8cbf18	Initial GPT-J support	2023-04-26 16:32:45 +02:00
niansa	aad1bd9ae4	Made Inference class virtual	2023-04-26 10:59:24 +02:00