gpt4all

Author	SHA1	Message	Date
AT	964e2ffc1b	We no longer have an avx_only repository and better error handling for minimum hardware requirements. (#833 )	1 year ago
Richard Guo	fb09f412ff	cleanup	1 year ago
Richard Guo	67b7641390	fixed finding model libs	1 year ago
Adam Treat	1b755b6cba	Try and fix build on mac.	1 year ago
Adam Treat	7ee32d605f	Trying to shrink the copy+paste code and do more code sharing between backend model impl.	1 year ago
niansa/tuxifan	c4f9535fd0	Allow user to specify custom search path via $GPT4ALL_IMPLEMENTATIONS_PATH (#789 )	1 year ago
niansa	ab56119470	Fixed double-free in LLModel::Implementation destructor	1 year ago
niansa/tuxifan	8aa707fdb4	Cleaned up implementation management (#787 ) * Cleaned up implementation management * Initialize LLModel::m_implementation to nullptr * llmodel.h: Moved dlhandle fwd declare above LLModel class	1 year ago
Adam Treat	8be42683ac	Add fixme's and clean up a bit.	1 year ago
niansa	b68d359b4f	Dlopen better implementation management (Version 2)	1 year ago
niansa/tuxifan	991a0e4bd8	Advanced avxonly autodetection (#744 ) * Advanced avxonly requirement detection	1 year ago
AT	9c6c09cbd2	Dlopen backend 5 (#779 ) Major change to the backend that allows for pluggable versions of llama.cpp/ggml. This was squashed merged from dlopen_backend_5 where the history is preserved.	1 year ago