196 Commits (e7c4680b51c0d29942981980769885314b5d0cc6)

Author	SHA1	Message	Date
Jared Van Bortel	7e9786fccf	chat: set search path early ... This fixes the issues with installed versions of v2.6.0.	8 months ago
AT	96cee4f9ac	Explicitly clear the kv cache each time we eval tokens to match n_past. (#1808)	8 months ago
ThiloteE	2d566710e5	Address review	8 months ago
ThiloteE	a0f7d7ae0e	Fix for "LLModel ERROR: Could not find CPU LLaMA implementation" v2	8 months ago
ThiloteE	38d81c14d0	Fixes https://github.com/nomic-ai/gpt4all/issues/1760 LLModel ERROR: Could not find CPU LLaMA implementation. ... Inspired by Microsoft docs for LoadLibraryExA (https://learn.microsoft.com/en-us/windows/win32/api/libloaderapi/nf-libloaderapi-loadlibraryexa). When using LOAD_LIBRARY_SEARCH_DLL_LOAD_DIR, the lpFileName parameter must specify a fully qualified path, also it needs to be backslashes (\), not forward slashes (/).	8 months ago
Jared Van Bortel	d1c56b8b28	Implement configurable context length (#1749)	9 months ago
Jared Van Bortel	3acbef14b7	fix AVX support by removing direct linking to AVX2 libs (#1750)	9 months ago
Jared Van Bortel	0600f551b3	chatllm: do not attempt to serialize incompatible state (#1742)	9 months ago
Jared Van Bortel	1df3da0a88	update llama.cpp for clang warning fix	9 months ago
Jared Van Bortel	dfd8ef0186	backend: use ggml_new_graph for GGML backend v2 (#1719)	9 months ago
Jared Van Bortel	9e28dfac9c	Update to latest llama.cpp (#1706)	9 months ago
Adam Treat	cce5fe2045	Fix macos build.	10 months ago
Adam Treat	371e2a5cbc	LocalDocs version 2 with text embeddings.	10 months ago
Jared Van Bortel	d4ce9f4a7c	llmodel_c: improve quality of error messages (#1625)	10 months ago
cebtenzzre	64101d3af5	update llama.cpp-mainline	10 months ago
Adam Treat	ffef60912f	Update to llama.cpp	10 months ago
Adam Treat	f5f22fdbd0	Update llama.cpp for latest bugfixes.	10 months ago
cebtenzzre	7bcd9e8089	update llama.cpp-mainline	10 months ago
cebtenzzre	fd0c501d68	backend: support GGUFv3 (#1582)	10 months ago
Adam Treat	14b410a12a	Update to latest version of llama.cpp which fixes issue 1507.	10 months ago
Adam Treat	ab96035bec	Update to llama.cpp submodule for some vulkan fixes.	11 months ago
cebtenzzre	e90263c23f	make scripts executable (#1555)	11 months ago
Aaron Miller	f414c28589	llmodel: whitelist library name patterns ... this fixes some issues that were being seen on installed windows builds of 2.5.0 only load dlls that actually might be model impl dlls, otherwise we pull all sorts of random junk into the process before it might expect to be Signed-off-by: Aaron Miller <apage43@ninjawhale.com>	11 months ago
cebtenzzre	4338e72a51	MPT: use upstream llama.cpp implementation (#1515)	11 months ago
cebtenzzre	0fe2e19691	llamamodel: re-enable error messages by default (#1537)	11 months ago
cebtenzzre	017c3a9649	python: prepare version 2.0.0rc1 (#1529)	11 months ago
cebtenzzre	9a19c740ee	kompute: fix library loading issues with kp_logger (#1517)	11 months ago
Aaron Miller	f79557d2aa	speedup: just use mat*vec shaders for mat*mat ... so far my from-scratch mat*mats are still slower than just running more invocations of the existing Metal ported mat*vec shaders - it should be theoretically possible to make a mat*mat that's faster (for actual mat*mat cases) than an optimal mat*vec, but it will need to be at *least* as fast as the mat*vec op and then take special care to be cache-friendly and save memory bandwidth, as the # of compute ops is the same	11 months ago
cebtenzzre	22de3c56bd	convert scripts: fix AutoConfig typo (#1512)	11 months ago
Aaron Miller	2490977f89	q6k, q4_1 mat*mat	11 months ago
Aaron Miller	afaa291eab	python bindings should be quiet by default ... * disable llama.cpp logging unless GPT4ALL_VERBOSE_LLAMACPP envvar is nonempty * make verbose flag for retrieve_model default false (but also be overridable via gpt4all constructor) should be able to run a basic test: ```python import gpt4all model = gpt4all.GPT4All('/Users/aaron/Downloads/rift-coder-v0-7b-q4_0.gguf') print(model.generate('def fib(n):')) ``` and see no non-model output when successful	11 months ago
cebtenzzre	7b611b49f2	llmodel: print an error if the CPU does not support AVX (#1499)	11 months ago
Aaron Miller	043617168e	do not process prompts on gpu yet	11 months ago
Aaron Miller	64001a480a	mat*mat for q4_0, q8_0	11 months ago
cebtenzzre	7a19047329	llmodel: do not call magic_match unless build variant is correct (#1488)	11 months ago
Cebtenzzre	5fe685427a	chat: clearer CPU fallback messages	11 months ago
Adam Treat	eec906aa05	Speculative fix for build on mac.	11 months ago
Adam Treat	a9acdd25de	Push a new version number for llmodel backend now that it is based on gguf.	11 months ago
Cebtenzzre	8bb6a6c201	rebase on newer llama.cpp	11 months ago
Cebtenzzre	d87573ea75	remove old llama.cpp submodules	11 months ago
Cebtenzzre	cc6db61c93	backend: fix build with Visual Studio generator ... Use the $<CONFIG> generator expression instead of CMAKE_BUILD_TYPE. This is needed because Visual Studio is a multi-configuration generator, so we do not know what the build type will be until `cmake --build` is called. Fixes #1470	11 months ago
Adam Treat	f605a5b686	Add q8_0 kernels to kompute shaders and bump to latest llama/gguf.	11 months ago
Cebtenzzre	672cb850f9	differentiate between init failure and unsupported models	11 months ago
Adam Treat	906699e8e9	Bump to latest llama/gguf branch.	11 months ago
Cebtenzzre	088afada49	llamamodel: fix static vector in LLamaModel::endTokens	11 months ago
Adam Treat	b4d82ea289	Bump to the latest fixes for vulkan in llama.	11 months ago
Adam Treat	12f943e966	Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.	11 months ago
Adam Treat	5d346e13d7	Add q6_k kernels for vulkan.	11 months ago
Adam Treat	4eefd386d0	Refactor for subgroups on mat * vec kernel.	11 months ago
Cebtenzzre	3c2aa299d8	gptj: remove unused variables	11 months ago