tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : fix LRU check (#14079)

Browse Source 
ggml-ci
This commit is contained in:
Georgi Gerganov
2025-06-09 12:57:58 +03:00
committed by GitHub
parent b460d16ae8
commit 87d34b381d
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
tools/server/server.cpp
View File

@ -2142,7 +2142,8 @@ struct server_context {
// find the slot that has been least recently used
if (ret == nullptr) {
int64_t t_last = ggml_time_us();
int64_t t_last = -1;
for (server_slot & slot : slots) {
// skip the slot if it is not available
if (slot.is_processing()) {
@ -2150,7 +2151,7 @@ struct server_context {
}
// select the current slot if the criteria match
if (slot.t_last_used < t_last) {
if (!ret || slot.t_last_used <= t_last) {
t_last = slot.t_last_used;
ret = &slot;
}