completion : fix prompt cache for recurrent models (#19045)

This commit is contained in:
Georgi Gerganov authored and GitHub committed 2026-01-25 09:12:50 +02:00
1 parent 1243f93a2d
commit 080b161995
2 files changed
+48 -41

No files matched your search

+1
View File
@@ -2559,6 +2559,7 @@ size_t llama_context::state_write_data(llama_io_write_i & io) {
}
}
// [TAG_CONTEXT_STATE_LOGITS]
// write logits
{
LLAMA_LOG_DEBUG("%s: - writing logits\n", __func__);