tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 21:15:06 +00:00
Code Issues Packages Projects Releases Wiki Activity

Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)

Browse Source 
* Use F16 for memory_k and memory_v

* add command line switch to use f16 instead of f32 for memory k+v

---------

Co-authored-by: Ty Everett <ty@tyweb.us>
This commit is contained in:
Erik Scholz
2023-03-19 18:57:00 +01:00
committed by GitHub
parent 160bfb217d
commit 0b366e7357
3 changed files with 11 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
utils.h
View File

@ -18,6 +18,7 @@ struct gpt_params {
int32_t n_predict = 128; // new tokens to predict
int32_t repeat_last_n = 64; // last n tokens to penalize
int32_t n_ctx = 512; //context size
bool memory_f16 = false; // use f16 instead of f32 for memory kv
// sampling parameters
int32_t top_k = 40;