124 Commits (0f046cf905067219b4030800beee778c98eae007)

Author	SHA1	Message	Date
Adam Treat	aa33419c6e	Fallback to CPU more robustly.	10 months ago
Adam Treat	9013a089bd	Bump to new llama with new bugfix.	10 months ago
Adam Treat	3076e0bf26	Only show GPU when we're actually using it.	10 months ago
Adam Treat	cf4eb530ce	Sync to a newer version of llama.cpp with bugfix for vulkan.	10 months ago
Adam Treat	4b9a345aee	Update the submodule.	10 months ago
Aaron Miller	6f038c136b	init at most one vulkan device, submodule update ... fixes issues w/ multiple of the same gpu	10 months ago
Adam Treat	8f99dca70f	Bring the vulkan backend to the GUI.	10 months ago
Aaron Miller	f0735efa7d	vulkan python bindings on windows fixes	10 months ago
Adam Treat	c953b321b7	Don't link against libvulkan.	10 months ago
Aaron Miller	c4d23512e4	remove extra dynamic linker deps when building with vulkan	10 months ago
Adam Treat	85e34598f9	more circleci	10 months ago
Adam Treat	f578fa6cdf	Fix for windows.	10 months ago
Adam Treat	17d3e4976c	Add a comment indicating future work.	10 months ago
Adam Treat	987546c63b	Nomic vulkan backend licensed under the Software for Open Models License (SOM), version 1.0.	10 months ago
Adam Treat	d55cbbee32	Update to newer llama.cpp and disable older forks.	10 months ago
Aaron Miller	0bc2274869	bump llama.cpp version + needed fixes for that	10 months ago
aaron miller	33c22be2aa	starcoder: use ggml_graph_plan	10 months ago
Cosmic Snow	108d950874	Fix Windows unable to load models on older Windows builds ... - Replace high-level IsProcessorFeaturePresent - Reintroduce low-level compiler intrinsics implementation	11 months ago
Adam Treat	6d03b3e500	Add starcoder support.	12 months ago
cosmic-snow	2d02c65177	Handle edge cases when generating embeddings (#1215) ... * Handle edge cases when generating embeddings * Improve Python handling & add llmodel_c.h note - In the Python bindings fail fast with a ValueError when text is empty - Advice other bindings authors to do likewise in llmodel_c.h	12 months ago
Aaron Miller	1c4a244291	bump mem allocation a bit	1 year ago
Adam Treat	ee4186d579	Fixup bert python bindings.	1 year ago
cosmic-snow	6200900677	Fix Windows MSVC arch detection (#1194) ... - in llmodel.cpp to fix AVX-only handling Signed-off-by: cosmic-snow <134004613+cosmic-snow@users.noreply.github.com>	1 year ago
Adam Treat	4963db8f43	Bump the version numbers for both python and c backend.	1 year ago
Adam Treat	0efdbfcffe	Bert	1 year ago
Adam Treat	315a1f2aa2	Move it back as internal class.	1 year ago
Adam Treat	ae8eb297ac	Add sbert backend.	1 year ago
Adam Treat	1f749d7633	Clean up backend code a bit and hide impl. details.	1 year ago
Adam Treat	33557b1f39	Move the implementation out of llmodel class.	1 year ago
Aaron Miller	432b7ebbd7	include windows.h just to be safe	1 year ago
Aaron Miller	95b8fb312e	windows/msvc: use high level processor feature detection API ... see https://learn.microsoft.com/en-us/windows/win32/api/processthreadsapi/nf-processthreadsapi-isprocessorfeaturepresent	1 year ago
Aaron Miller	f0faa23ad5	cmakelists: always export build commands (#1179) ... friendly for using editors with clangd integration that don't also manage the build themselves	1 year ago
Aaron Miller	4a24b586df	llama.cpp: metal buffer freeing	1 year ago
Aaron Miller	137bc2c367	replit: free metal context	1 year ago
Aaron Miller	57dc0c8953	adjust eval buf sizes to pass long input test	1 year ago
Aaron Miller	7a5f6e4726	limit prompt batch size to 128	1 year ago
Aaron Miller	883775bc5f	move 230511 submodule to nomic fork, fix alibi assert	1 year ago
Andriy Mulyar	46a0762bd5	Python Bindings: Improved unit tests, documentation and unification of API (#1090) ... * Makefiles, black, isort * Black and isort * unit tests and generation method * chat context provider * context does not reset * Current state * Fixup * Python bindings with unit tests * GPT4All Python Bindings: chat contexts, tests * New python bindings and backend fixes * Black and Isort * Documentation error * preserved n_predict for backwords compat with langchain --------- Co-authored-by: Adam Treat <treat.adam@gmail.com>	1 year ago
Aaron Miller	40a3faeb05	Use ggml scratch bufs for mpt and gptj models (#1104) ... * backend/gptj: use scratch buffers reduces total memory required and makes eval buf not grow with n_past * backend/mpt: use scratch bufs * fix format-related compile warnings	1 year ago
Aaron Miller	8d19ef3909	backend: factor out common elements in model code (#1089) ... * backend: factor out common structs in model code prepping to hack on these by hopefully making there be fewer places to fix the same bug rename * use common buffer wrapper instead of manual malloc * fix replit compile warnings	1 year ago
Aaron Miller	28d41d4f6d	falcon: use *model-local* eval & scratch bufs (#1079) ... fixes memory leaks copied from ggml/examples based implementation	1 year ago
Zach Nussbaum	2565f6a94a	feat: add conversion script	1 year ago
Aaron Miller	198b5e4832	add Falcon 7B model ... Tested with https://huggingface.co/TheBloke/falcon-7b-instruct-GGML/blob/main/falcon7b-instruct.ggmlv3.q4_0.bin	1 year ago
Aaron Miller	db34a2f670	llmodel: skip attempting Metal if model+kvcache > 53% of system ram	1 year ago
Aaron Miller	b19a3e5b2c	add requiredMem method to llmodel impls ... most of these can just shortcut out of the model loading logic llama is a bit worse to deal with because we submodule it so I have to at least parse the hparams, and then I just use the size on disk as an estimate for the mem size (which seems reasonable since we mmap() the llama files anyway)	1 year ago
Adam Treat	a0f80453e5	Use sysinfo in backend.	1 year ago
niansa/tuxifan	47323f8591	Update replit.cpp ... replit_tokenizer_detokenize returnins std::string now Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>	1 year ago
niansa	0855c0df1d	Fixed Replit implementation compile warnings	1 year ago
Aaron Miller	1290b32451	update to latest mainline llama.cpp ... add max_size param to ggml_metal_add_buffer - introduced in https://github.com/ggerganov/llama.cpp/pull/1826	1 year ago
niansa/tuxifan	5eee16c97c	Do not specify "success" as error for unsupported models ... Signed-off-by: niansa/tuxifan <tuxifan@posteo.de>	1 year ago