From e36ecdccc8754783f93ad3ac8a09e540101f2ca0 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Mon, 4 Sep 2023 22:26:24 +0300 Subject: build : on Mac OS enable Metal by default (#2901) * build : on Mac OS enable Metal by default * make : try to fix build on Linux * make : move targets back to the top * make : fix target clean * llama : enable GPU inference by default with Metal * llama : fix vocab_only logic when GPU is enabled * common : better `n_gpu_layers` assignment * readme : update Metal instructions * make : fix merge conflict remnants * gitignore : metal --- common/common.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'common/common.h') diff --git a/common/common.h b/common/common.h index 105fb09e..85ac0df9 100644 --- a/common/common.h +++ b/common/common.h @@ -34,7 +34,7 @@ struct gpt_params { int32_t n_keep = 0; // number of tokens to keep from initial prompt int32_t n_draft = 16; // number of tokens to draft during speculative decoding int32_t n_chunks = -1; // max number of chunks to process (-1 = unlimited) - int32_t n_gpu_layers = 0; // number of layers to store in VRAM + int32_t n_gpu_layers = -1; // number of layers to store in VRAM (-1 - use default) int32_t main_gpu = 0; // the GPU that is used for scratch and small tensors float tensor_split[LLAMA_MAX_DEVICES] = {0}; // how split tensors should be distributed across GPUs int32_t n_probs = 0; // if greater than 0, output the probabilities of top n_probs tokens. -- cgit v1.2.3