tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-29 04:35:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

speculative: add --n-gpu-layers-draft option (#3063)

Browse Source
This commit is contained in:
FK
2023-09-13 08:50:46 +02:00
committed by GitHub
parent b52b29ab9d
commit 84e723653c
3 changed files with 15 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
common/common.h
View File

@ -38,6 +38,7 @@ struct gpt_params {
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 = -1; // number of layers to store in VRAM (-1 - use default)
int32_t n_gpu_layers_draft = -1; // number of layers to store in VRAM for the draft model (-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.