mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-06-28 12:25:03 +00:00
server: free sampling contexts on exit (#7264)
* server: free sampling contexts on exit This cleans up last leak found by the address sanitizer. * fix whitespace * fix whitespace
This commit is contained in:
@ -671,6 +671,13 @@ struct server_context {
|
||||
model = nullptr;
|
||||
}
|
||||
|
||||
// Clear any sampling context
|
||||
for (server_slot & slot : slots) {
|
||||
if (slot.ctx_sampling != nullptr) {
|
||||
llama_sampling_free(slot.ctx_sampling);
|
||||
}
|
||||
}
|
||||
|
||||
llama_batch_free(batch);
|
||||
}
|
||||
|
||||
|
Reference in New Issue
Block a user