152 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
niansa	449a25c360	Use option() in CMake	2024-03-25 01:19:05 +01:00
niansa	90e54d66d0	Removed cosched support	2024-03-25 01:18:37 +01:00
niansa	1a04a0e6d9	Updated llama.cpp-mainline	2023-12-25 16:55:30 +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	f5314a0dde	Added python bindings for grammar	2023-09-05 09:27:45 +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	cb683aa8fc	Updated llama.cpp.cmake	2023-08-31 17:00:50 +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	08ff1e72e7	Update llama.cpp-mainline	2023-06-25 01:18:57 +02:00
niansa	01b0d059ed	Added pre_tick	2023-06-15 18:14:09 +02:00
niansa	bcacfc3d54	Minor CMake fixes	2023-06-10 02:04:50 +02:00
niansa	0199db02b7	Added GPU support	2023-06-10 00:49:21 +02:00
niansa	e2f7da65e4	Fixed llama.cpp not generating symbols	2023-06-10 00:38:38 +02:00
niansa	94953cd174	Improve some error handling macros	2023-06-09 23:53:01 +02:00
niansa	24849804b6	Major CMake improvements	2023-06-09 20:01:49 +02:00
niansa	b3bd78b350	Fixups in llama.cpp.cmake	2023-06-09 19:43:29 +02:00
niansa	a03558ae89	Expose options	2023-06-09 19:39:24 +02:00
niansa	38b229dab5	Updated to latest functional llama version	2023-06-09 12:01:41 +02:00
niansa	09e59a9536	Fixed compile errors because of previous commit	2023-05-31 20:22:18 +02:00
niansa	0142db3f7c	Renamed operator ""_MB -> operator ""_MiB	2023-05-31 20:20:31 +02:00
niansa	2d57ade1b8	add msvc support -polyfill unistd	2023-05-31 19:56:40 +02:00
niansa	4b19bc49a5	Fixed llama.cpp.cmake	2023-05-26 13:44:26 +02:00
niansa	53a4623aef	Added mirostat support	2023-05-26 00:43:07 +02:00
niansa	ad0b7e3c71	Updated llama.cpp-mainline	2023-05-23 13:41:30 +02:00
niansa	24ff52919f	Renamed justlm_llama_old to justlm_llama_230511	2023-05-21 16:13:51 +02:00
niansa	fe850337df	Pass context to llama_sample_repetition_penalty	2023-05-21 15:40:49 +02:00
niansa	e69157764b	Fixed capitalization of justLM_LLAMA_OLD target	2023-05-21 15:39:27 +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	c9dac7cb89	Fixed file type detection	2023-05-19 17:45:32 +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	b17cc6ffbd	Final fixup step #3	2023-05-19 16:20:51 +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	b5e10d1fa3	Use magic to identify llama models	2023-05-19 02:40:57 +02:00
niansa	f279b31d5f	Minor improvemens in CMakeFiles and dlhandle	2023-05-18 22:32:06 +02:00
niansa	e489f0f53c	Removed now-dead allocation from mpt_model	2023-05-18 22:32:06 +02:00
niansa	8fbbf58622	Removed magic_match for llama.cpp	2023-05-18 17:49:22 +00:00
niansa	88e35fd25d	Fixed output directory	2023-05-18 17:48:54 +00:00
niansa	a0ec6f8a11	Fixed . being used instead of ${DIRECTORY} in llama.cpp.cmake	2023-05-17 19:01:08 +00:00