Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	AGENTS.md
#	build-xcframework.sh
This commit is contained in:
Concedo
2026-06-04 23:44:05 +08:00
parent 2750cc492b 21444c822e
commit af3bcde675
22 changed files with 1512 additions and 1094 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tools/server/server-context.cpp
+4 -1
View File
@@ -2782,8 +2782,11 @@ private:
llama_pos pos_next = slot.prompt.tokens.pos_next(n_past);
// ref: https://github.com/ggml-org/llama.cpp/pull/24110
const bool has_new_tokens = (n_past < slot.task->n_tokens());
// the largest pos_min required for a checkpoint to be useful
const auto pos_min_thold = std::max(0, pos_next - n_swa - 1);
const auto pos_min_thold = std::max(0, pos_next - n_swa - (has_new_tokens ? 0 : 1));
if (n_past > 0 && n_past <= slot.prompt.n_tokens()) {
const auto pos_min = llama_memory_seq_pos_min(llama_get_memory(ctx_tgt), slot.id);