CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-30 08:42:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : fix find_slot to not search for continuous slot (#15638)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-08-28 17:09:05 +03:00
committed by GitHub
parent 84ab83cc0b
commit c8d0d14e77
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/llama-kv-cache.cpp
View File

@@ -540,7 +540,7 @@ llama_kv_cache::slot_info_vec_t llama_kv_cache::prepare(const std::vector<llama_
for (const auto & ubatch : ubatches) { for (const auto & ubatch : ubatches) {
// only find a suitable slot for the ubatch. don't modify the cells yet // only find a suitable slot for the ubatch. don't modify the cells yet
const auto sinfo_new = find_slot(ubatch, true); const auto sinfo_new = find_slot(ubatch, false);
if (sinfo_new.empty()) { if (sinfo_new.empty()) {
success = false; success = false;
break; break;