Skip to content

Commit 56e82d0

Browse files
committed
fix server
1 parent 42062cc commit 56e82d0

File tree

1 file changed

+1
-1
lines changed

1 file changed

+1
-1
lines changed

examples/server/server.cpp

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1959,7 +1959,7 @@ struct server_context {
19591959

19601960
// the update_slots() logic will always submit a maximum of n_batch or n_parallel tokens
19611961
// note that n_batch can be > n_ctx (e.g. for non-causal attention models such as BERT where the KV cache is not used)
1962-
batch.clear();
1962+
batch = llama_batch_ext_ptr(ctx);
19631963
metrics.init();
19641964
}
19651965

0 commit comments

Comments
 (0)