tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 03:55:20 +00:00
Code Issues Packages Projects Releases Wiki Activity

llama : minor sampling refactor (2) (#9386)

Browse Source
This commit is contained in:
slaren
2024-09-09 17:10:46 +02:00
committed by GitHub
parent 38ca6f644b
commit 5fb5e24811
12 changed files with 115 additions and 113 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
examples/save-load-state/save-load-state.cpp
View File

@ -74,8 +74,6 @@ int main(int argc, char ** argv) {
auto next_token = llama_sampler_sample(smpl, ctx, -1);
auto next_token_str = llama_token_to_piece(ctx, next_token);
llama_sampler_accept(smpl, next_token);
printf("%s", next_token_str.c_str());
result0 += next_token_str;
@ -132,8 +130,6 @@ int main(int argc, char ** argv) {
auto next_token = llama_sampler_sample(smpl2, ctx2, -1);
auto next_token_str = llama_token_to_piece(ctx2, next_token);
llama_sampler_accept(smpl2, next_token);
printf("%s", next_token_str.c_str());
result1 += next_token_str;
@ -222,8 +218,6 @@ int main(int argc, char ** argv) {
auto next_token = llama_sampler_sample(smpl3, ctx3, -1);
auto next_token_str = llama_token_to_piece(ctx3, next_token);
llama_sampler_accept(smpl3, next_token);
printf("%s", next_token_str.c_str());
result2 += next_token_str;