tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-07-11 22:04:31 +00:00
Code Issues Packages Projects Releases Wiki Activity

kv-cache : fix handling when find_slot fails

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-07-04 17:59:08 +03:00
parent 280b0b9a04
commit 5c00eb22f2
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-unified.cpp
View File

@ -573,7 +573,7 @@ llama_kv_cache_unified::slot_info_vec_t llama_kv_cache_unified::prepare(const st
apply_ubatch(sinfo_new, ubatch);
}
GGML_ASSERT(!states.empty());
GGML_ASSERT(!states.empty() || !success);
// iterate backwards and restore the cells to their original state
for (auto it = states.rbegin(); it != states.rend(); ++it) {