CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-11-04 09:32:00 +00:00
Code Issues Packages Projects Releases Wiki Activity

memory : correctly handle failure in apply() (#14438)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-30 18:03:03 +03:00
committed by GitHub
parent 5dd942de59
commit 745f11fed0
6 changed files with 32 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1776,7 +1776,7 @@ bool llama_kv_cache_unified_context::next() {
}
bool llama_kv_cache_unified_context::apply() {
assert(status == LLAMA_MEMORY_STATUS_SUCCESS);
assert(!llama_memory_status_is_fail(status));
// no ubatches -> this is a KV cache update
if (ubatches.empty()) {