server : enable multi-modal prompt caching (#19877)

This commit is contained in:
Georgi Gerganov
2026-02-25 15:15:42 +02:00
committed by GitHub
parent d7d826b3c1
commit f20469d919
2 changed files with 1 additions and 5 deletions
-3
View File
@@ -995,9 +995,6 @@ private:
// don't update the cache if the slot's context is empty
update_cache = update_cache && tokens.size() > 0;
// TODO: mtmd does not support prompt cache
update_cache = update_cache && (ret->mctx == nullptr);
if (update_cache) {
SRV_WRN("%s", "updating prompt cache\n");