tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-01 05:05:10 +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

2
examples/llama.android/llama/src/main/cpp/llama-android.cpp
View File

@ -414,8 +414,6 @@ Java_android_llama_cpp_LLamaAndroid_completion_1loop(
// sample the most likely token
const auto new_token_id = llama_sampler_sample(sampler, context, -1);
llama_sampler_accept(sampler, new_token_id);
const auto n_cur = env->CallIntMethod(intvar_ncur, la_int_var_value);
if (llama_token_is_eog(model, new_token_id) || n_cur == n_len) {
return nullptr;