baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

Handle very slow model loads

Browse source 
During testing, we're seeing some models take over 3 minutes.
This commit is contained in:
Daniel Hiltgen 2024-04-09 16:35:10 -07:00
parent 1524f323a3
commit c5ff443b9f
1 changed files with 2 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

3
llm/server.go
View file

@ -383,7 +383,8 @@ func (s *LlamaServer) Ping(ctx context.Context) error {
func (s *LlamaServer) waitUntilRunning() error {
start := time.Now()
expiresAt := time.Now().Add(3 * time.Minute) // be generous with timeout, large models can take a while to load
// TODO we need to wire up a better way to detect hangs during model load and startup of the server
expiresAt := time.Now().Add(10 * time.Minute) // be generous with timeout, large models can take a while to load
ticker := time.NewTicker(50 * time.Millisecond)
defer ticker.Stop()