cturan/llama.cpp

mirror of https://github.com/cturan/llama.cpp

Author	SHA1 Message	Date
Georgi Gerganov	edd4c14817 llama : more tokenizer fixes (#2810)	2 years ago
Matt Pulver	c82742ac9c llama : add llama_beam_search() (#2267)	2 years ago
Georgi Gerganov	cf658adc83 llm : add Falcon support (#2717)	2 years ago
Kawrakow	62959e740e Strided perplexity (#2714)	2 years ago
Johannes Gäßler	c63bb1d16a CUDA: use mul_mat_q kernels by default (#2683)	2 years ago
Georgi Gerganov	6381d4e110 gguf : new file format with flexible meta data (beta) (#2398)	2 years ago