tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-09-01 21:04:58 -04:00
Code Issues Packages Projects Releases Wiki Activity

llama : adjust default context size + print warnings (#10136)

Browse Source 
* llama : adjust default context size + print warnings

ggml-ci

* ggml-ci : add missing gpu-layers + adjust context sizes
This commit is contained in:
Georgi Gerganov
2024-11-02 15:18:56 +02:00
committed by GitHub
parent b634f8a26f
commit 1926d6e39d
3 changed files with 103 additions and 89 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
common/common.h
View File

@@ -155,7 +155,7 @@ struct common_sampler_params {
struct common_params {
int32_t n_predict = -1; // new tokens to predict
int32_t n_ctx = 0; // context size
int32_t n_ctx = 4096; // context size
int32_t n_batch = 2048; // logical batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_ubatch = 512; // physical batch size for prompt processing (must be >=32 to use BLAS)
int32_t n_keep = 0; // number of tokens to keep from initial prompt