Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

ramalama server - CTRL C not working and freeze terminal #753

Closed
dougsland opened this issue Feb 6, 2025 · 3 comments · Fixed by #785
Closed

ramalama server - CTRL C not working and freeze terminal #753

dougsland opened this issue Feb 6, 2025 · 3 comments · Fixed by #785

Comments

@dougsland
Copy link
Collaborator

Terminal stopped responding

ramalama serve tinyllama --host 0.0.0.0 
main: server is listening on http://0.0.0.0:8080 - starting the main loop
srv  update_slots: all slots are idle
slot launch_slot_: id  0 | task 0 | processing task
slot update_slots: id  0 | task 0 | new prompt, n_ctx_slot = 2048, n_keep = 0, n_prompt_tokens = 7
slot update_slots: id  0 | task 0 | kv cache rm [0, end)
slot update_slots: id  0 | task 0 | prompt processing progress, n_past = 7, n_tokens = 7, progress = 1.000000
slot update_slots: id  0 | task 0 | prompt done, n_past = 7, n_tokens = 7
slot      release: id  0 | task 0 | stop processing: n_past = 99, truncated = 0
slot print_timing: id  0 | task 0 | 
prompt eval time =      47.81 ms /     7 tokens (    6.83 ms per token,   146.41 tokens per second)
       eval time =    1350.11 ms /    93 tokens (   14.52 ms per token,    68.88 tokens per second)
      total time =    1397.92 ms /   100 tokens
srv  update_slots: all slots are idle
^C^C^C^C^C^C^C^C^C

To get shell back, used:

ps aux | grep ramalama | awk '{print }' | xargs kill -9 
ps aux | grep 8080 | xargs kill -9 

Terminal macOS v2.14 (155)

@rhatdan
Copy link
Member

rhatdan commented Feb 7, 2025

You need to do ramalama stop in a separate window.

Could you check if you do an exec into the container and see if llama-serve is ignoring SIGTERM

podman exec -l kill TERM 1

@rhatdan
Copy link
Member

rhatdan commented Feb 7, 2025

I just checked this is definitely a llama-serve issue.

@rhatdan
Copy link
Member

rhatdan commented Feb 7, 2025

ggerganov/llama.cpp#11742

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging a pull request may close this issue.

2 participants