completion : fix prompt cache for recurrent models (#19045)
This commit is contained in:
@@ -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__);
|
||||
|
||||
Reference in New Issue
Block a user