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

fix sched to wait for the runner to terminate to ensure following vram check will be more accurate

Browse source
This commit is contained in:
Mark Ward 2024-04-28 16:41:38 +00:00
parent a3e60d9058
commit 948114e3e3
1 changed files with 4 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
llm/server.go
View file

@ -899,7 +899,10 @@ func (s *llmServer) Detokenize(ctx context.Context, tokens []int) (string, error
func (s *llmServer) Close() error {
if s.cmd != nil {
slog.Debug("stopping llama server")
return s.cmd.Process.Kill()
if err := s.cmd.Process.Kill(); err != nil {
return err
}
return s.cmd.Wait()
}
return nil