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

A very long start server #4027

Open
sh1man opened this issue Mar 18, 2025 · 2 comments
Open

A very long start server #4027

sh1man opened this issue Mar 18, 2025 · 2 comments

Comments

@sh1man
Copy link

sh1man commented Mar 18, 2025

I waited 40 minutes for the launch. After rebooting, the same thing happens

Describe the bug
log file
Writing to new file.
✅ Checksum OK.

⠋ 0.000 s Starting...
⠙ 0.080 s Starting...
⠹ 0.161 s Starting...
⠸ 0.241 s Starting...
....
https://pastebin.com/

services:
  tabby:
    image: tabbyml/tabby
    container_name: tabby
    restart: unless-stopped
    ports:
      - "8080:8080"
    volumes:
      - ${HOME}/.tabby:/data
    environment:
      - TABBY_DISABLE_USAGE_COLLECTION=1
    command: serve --model Qwen2.5-Coder-3B --device cuda --chat-model Qwen2-1.5B-Instruct
    deploy:
      resources:
        reservations:
          devices:
            - driver: nvidia
              count: all
              capabilities: [gpu]


Information about your version
tabby version latest docker

Information about your GPU

NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4

Additional context
Add any other context about the problem here.

@wsxiaoys
Copy link
Member

Hi - can you include output of nvidia-smi in issue description?

@sh1man
Copy link
Author

sh1man commented Mar 18, 2025

❯ nvidia-smi
Tue Mar 18 13:25:47 2025
+-----------------------------------------------------------------------------------------+
| NVIDIA-SMI 550.120 Driver Version: 550.120 CUDA Version: 12.4 |
|-----------------------------------------+------------------------+----------------------+
| GPU Name Persistence-M | Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap | Memory-Usage | GPU-Util Compute M. |
| | | MIG M. |
|=========================================+========================+======================|
| 0 NVIDIA GeForce RTX 3060 Ti Off | 00000000:03:00.0 On | N/A |
| 0% 45C P2 44W / 200W | 611MiB / 8192MiB | 1% Default |
| | | N/A |
+-----------------------------------------+------------------------+----------------------+

+-----------------------------------------------------------------------------------------+
| Processes: |
| GPU GI CI PID Type Process name GPU Memory |
| ID ID Usage |
|=========================================================================================|
| 0 N/A N/A 3537 G /usr/lib/xorg/Xorg 268MiB |
| 0 N/A N/A 3859 G /usr/bin/gnome-shell 90MiB |
| 0 N/A N/A 5582 G ...85,262144 --variations-seed-version 65MiB |
| 0 N/A N/A 6865 G /usr/bin/x-terminal-emulator 9MiB |
| 0 N/A N/A 9487 G /app/bin/telegram-desktop 2MiB |
| 0 N/A N/A 22912 C /opt/tabby/bin/llama-server 146MiB |
| 0 N/A N/A 23902 G /usr/bin/x-terminal-emulator 9MiB |
+-----------------------------------------------------------------------------------------+

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

No branches or pull requests

2 participants