vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-19 08:00:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/workflows/build.yml
#	.github/workflows/release.yml
#	CMakeLists.txt
#	examples/simple-chat/simple-chat.cpp
#	src/llama-quant.cpp
#	tools/run/run.cpp
#	tools/server/README.md
This commit is contained in:
Concedo 2025-06-24 23:06:16 +08:00
commit ace537d44e
17 changed files with 554 additions and 212 deletions
Download patch file Download diff file Expand all files Collapse all files

1
src/llama-context.cpp
View file

@ -1018,7 +1018,6 @@ int llama_context::decode(const llama_batch & batch_inp) {
pos_min[s] = std::numeric_limits<llama_pos>::max();
}
// TODO: fix sequence indexing
for (uint32_t i = 0; i < ubatch.n_tokens; ++i) {
const auto & seq_id = ubatch.seq_id[i][0];