175 Commits (8d7a3f26d34be411f2f4da902326d560bcbfa38b)

Author	SHA1	Message	Date
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)	12 months ago
cebtenzzre	0fe2e19691	llamamodel: re-enable error messages by default (#1537)	12 months ago
cebtenzzre	017c3a9649	python: prepare version 2.0.0rc1 (#1529)	12 months ago
cebtenzzre	9a19c740ee	kompute: fix library loading issues with kp_logger (#1517)	12 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	12 months ago
cebtenzzre	22de3c56bd	convert scripts: fix AutoConfig typo (#1512)	12 months ago
Aaron Miller	2490977f89	q6k, q4_1 mat*mat	12 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	12 months ago
cebtenzzre	7b611b49f2	llmodel: print an error if the CPU does not support AVX (#1499)	12 months ago
Aaron Miller	043617168e	do not process prompts on gpu yet	12 months ago
Aaron Miller	64001a480a	mat*mat for q4_0, q8_0	12 months ago
cebtenzzre	7a19047329	llmodel: do not call magic_match unless build variant is correct (#1488)	12 months ago
Cebtenzzre	5fe685427a	chat: clearer CPU fallback messages	12 months ago
Adam Treat	eec906aa05	Speculative fix for build on mac.	12 months ago
Adam Treat	a9acdd25de	Push a new version number for llmodel backend now that it is based on gguf.	12 months ago
Cebtenzzre	8bb6a6c201	rebase on newer llama.cpp	12 months ago
Cebtenzzre	d87573ea75	remove old llama.cpp submodules	12 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	12 months ago
Adam Treat	f605a5b686	Add q8_0 kernels to kompute shaders and bump to latest llama/gguf.	12 months ago
Cebtenzzre	672cb850f9	differentiate between init failure and unsupported models	12 months ago
Adam Treat	906699e8e9	Bump to latest llama/gguf branch.	12 months ago
Cebtenzzre	088afada49	llamamodel: fix static vector in LLamaModel::endTokens	12 months ago
Adam Treat	b4d82ea289	Bump to the latest fixes for vulkan in llama.	12 months ago
Adam Treat	12f943e966	Fix regenerate button to be deterministic and bump the llama version to latest we have for gguf.	12 months ago
Adam Treat	5d346e13d7	Add q6_k kernels for vulkan.	12 months ago
Adam Treat	4eefd386d0	Refactor for subgroups on mat * vec kernel.	12 months ago
Cebtenzzre	3c2aa299d8	gptj: remove unused variables	12 months ago
Cebtenzzre	f9deb87d20	convert scripts: add feed-forward length for better compatiblilty ... This GGUF key is used by all llama.cpp models with upstream support.	12 months ago
Cebtenzzre	cc7675d432	convert scripts: make gptj script executable	12 months ago
Cebtenzzre	0493e6eb07	convert scripts: use bytes_to_unicode from transformers	12 months ago
Cebtenzzre	d5d72f0361	gpt-j: update inference to match latest llama.cpp insights ... - Use F16 KV cache - Store transposed V in the cache - Avoid unnecessary Q copy Co-authored-by: Georgi Gerganov <ggerganov@gmail.com> ggml upstream commit 0265f0813492602fec0e1159fe61de1bf0ccaf78	12 months ago
Cebtenzzre	050e7f076e	backend: port GPT-J to GGUF	12 months ago
Cebtenzzre	8f3abb37ca	fix references to removed model types	12 months ago
Cebtenzzre	4219c0e2e7	convert scripts: make them directly executable	12 months ago
Cebtenzzre	ce7be1db48	backend: use llamamodel.cpp for Falcon	12 months ago
Cebtenzzre	cca9e6ce81	convert_mpt_hf_to_gguf.py: better tokenizer decoding	12 months ago
Cebtenzzre	25297786db	convert scripts: load model as late as possible	12 months ago
Cebtenzzre	fd47088f2b	conversion scripts: cleanup	12 months ago
Cebtenzzre	6277eac9cc	backend: use llamamodel.cpp for StarCoder	12 months ago
Cebtenzzre	17fc9e3e58	backend: port Replit to GGUF	12 months ago
Cebtenzzre	7c67262a13	backend: port MPT to GGUF	12 months ago
Cebtenzzre	42bcb814b3	backend: port BERT to GGUF	12 months ago
Cebtenzzre	1d29e4696c	llamamodel: metal supports all quantization types now	12 months ago
Aaron Miller	507753a37c	macos build fixes	12 months ago
Adam Treat	d90d003a1d	Latest rebase on llama.cpp with gguf support.	12 months ago
Adam Treat	99c106e6b5	Fix a bug seen on AMD RADEON cards with vulkan backend.	1 year ago
Jacob Nguyen	e86c63750d	Update llama.cpp.cmake ... Signed-off-by: Jacob Nguyen <76754747+jacoobes@users.noreply.github.com>	1 year ago
Adam Treat	84905aa281	Fix for crashes on systems where vulkan is not installed properly.	1 year ago