server : refactored the task processing logic (#5065)
* server: add llama_server_queue struct * server: add llama_server_response_event * server: add comments * server: move all mutexes away from server.cpp * server: correct multitask response * server: only add back deferred tasks when one slot is available * server: fix a race condition cause by "request_completion"
This commit is contained in:
1 parent
413e7b0559
commit
48c857aa10
5 files changed
+876
-692
No files matched your search
+159
-690
File diff suppressed because it is too large.
Load diff
Reference in new issue
Block a user