You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

Mikko Juola 91dee4f114 Add --quiet flag, make colors respect --quiet so you just get the output and nothing else.		3 years ago
..
benches	Make matrix multiplication multithreaded.	3 years ago
protomodels	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
embedding.rs	Add support for bigger models.	3 years ago
lib.rs	Add some beginnings of OpenCL implementation.	3 years ago
main.rs	First commit. LLaMA works now. It is not pretty but it does generate text from prompts. Yay.	3 years ago
rllama_main.rs	Add --quiet flag, make colors respect --quiet so you just get the output and nothing else.	3 years ago
tensor.rs	Make number of threads configurable and obtained by default from the system rather than hardcoding to 32.	3 years ago
tensor_opencl_support.rs	Some code cleanup in OpenCL.	3 years ago
token_sampler.rs	Improve matrix multiplication transposed further, this gives around ~10%-20% further increase by improving memory load to instruction ratio.	3 years ago
tokenizer.rs	Improve matrix multiplication transposed further, this gives around ~10%-20% further increase by improving memory load to instruction ratio.	3 years ago
transformer.rs	Make matrix multiplication multithreaded.	3 years ago
unpickler.rs	Improve matrix multiplication transposed further, this gives around ~10%-20% further increase by improving memory load to instruction ratio.	3 years ago