tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-28 20:25:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: mmq CLI option, fixed mmq build issues (#2453)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-07-31 15:44:35 +02:00
committed by GitHub
parent 1215ed7d5c
commit 0728c5a8b9
10 changed files with 67 additions and 27 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
examples/common.h
View File

@ -74,6 +74,7 @@ struct gpt_params {
size_t hellaswag_tasks = 400; // number of tasks to use when computing the HellaSwag score
bool low_vram = false; // if true, reduce VRAM usage at the cost of performance
bool mul_mat_q = false; // if true, use experimental mul_mat_q kernels
bool memory_f16 = true; // use f16 instead of f32 for memory kv
bool random_prompt = false; // do not randomize prompt if none provided
bool use_color = false; // use color to distinguish generations and inputs