thek0tyara/llama-cpp-turboquant
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 4

server: add auto-sleep after N seconds of idle (#18228)

Browse source 
* implement sleeping at queue level

* implement server-context suspend

* add test

* add docs

* optimization: add fast path

* make sure to free llama_init

* nits

* fix use-after-free

* allow /models to be accessed during sleeping, fix use-after-free

* don't allow accessing /models during sleep, it is not thread-safe

* fix data race on accessing props and model_meta

* small clean up

* trailing whitespace

* rm outdated comments
This commit is contained in:
Xuan-Son Nguyen 2025-12-21 02:24:42 +01:00 • committed by GitHub
parent 52ab19df63
commit ddcb75dd8a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
12 changed files with 355 additions and 122 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tools/server/server-context.h
View file

@ -22,9 +22,6 @@ struct server_context {
server_context();
~server_context();
// initialize slots and server-related data
void init();
// load the model and initialize llama_context
// returns true on success
bool load_model(const common_params & params);
@ -35,7 +32,7 @@ struct server_context {
// terminate main loop (will unblock start_loop)
void terminate();
// get the underlaying llama_context
// get the underlaying llama_context, can return nullptr if sleeping
llama_context * get_llama_context() const;
// get a new response reader, used by CLI application