vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

set n_batch to 512 for all cases

Browse source
This commit is contained in:
eiery 2023-04-22 00:07:42 -04:00
parent 131159ff1b
commit b2e8a320c8
1 changed files with 1 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

3
examples/common.h
View file

@ -2,7 +2,6 @@
#pragma once
#include "ggml.h"
#include "llama.h"
#include <string>
@ -21,7 +20,7 @@ struct gpt_params {
int32_t repeat_last_n = 64; // last n tokens to penalize
int32_t n_parts = -1; // amount of model parts (-1 = determine from model dimensions)
int32_t n_ctx = 512; // context size
int32_t n_batch = ggml_cpu_has_blas() ? 512 : 8; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_batch = 512; // batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt
// sampling parameters