Skip to content

Commit 42062cc

Browse files
committed
fix build
1 parent c4fea7f commit 42062cc

File tree

2 files changed

+1
-9
lines changed

2 files changed

+1
-9
lines changed

examples/parallel/parallel.cpp

Lines changed: 0 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -158,8 +158,6 @@ int main(int argc, char ** argv) {
158158

159159
LOG_INF("\n\n");
160160

161-
const int n_ctx = llama_n_ctx(ctx);
162-
163161
std::vector<client> clients(n_clients);
164162
for (size_t i = 0; i < clients.size(); ++i) {
165163
auto & client = clients[i];

examples/server/server.cpp

Lines changed: 1 addition & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -1959,13 +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-
{
1963-
const int32_t n_batch = llama_n_batch(ctx);
1964-
1965-
// only a single seq_id per token is needed
1966-
batch.clear();
1967-
}
1968-
1962+
batch.clear();
19691963
metrics.init();
19701964
}
19711965

0 commit comments

Comments
 (0)