vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-15 11:29:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	Makefile
#	README.md
#	common/CMakeLists.txt
#	common/common.cpp
#	common/common.h
#	examples/embedding/embedding.cpp
#	examples/imatrix/imatrix.cpp
#	examples/infill/infill.cpp
#	examples/parallel/parallel.cpp
#	examples/perplexity/perplexity.cpp
#	examples/rpc/README.md
#	examples/save-load-state/save-load-state.cpp
#	examples/server/README.md
#	examples/speculative/speculative.cpp
#	tests/test-sampling.cpp
This commit is contained in:
Concedo 2024-09-10 16:39:23 +08:00
commit a947558e0e
45 changed files with 2628 additions and 6743 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;