Cannot deploy deepseek NIM

AI & Data Science NVIDIA NIM
1

HI, I followed the instruction: deepseek-r1 Model by Deepseek-ai | NVIDIA NIM to deploy deepseek docker and got the following error:

WARNING 06-26 00:11:48 cuda.py:22] You are using a deprecated pynvml package. Please install nvidia-ml-py instead, and make sure to uninstall pynvml. When both of them are installed, pynvml will take precedence and cause errors. See Client Challenge for more information.

INFO 2025-06-26 00:11:58.572 ngc_profile.py:339] Running NIM without LoRA. Only looking for compatible profiles that do not support LoRA.
INFO 2025-06-26 00:11:58.572 ngc_profile.py:341] Detected 0 compatible profile(s).
ERROR 2025-06-26 00:11:58.572 utils.py:24] Could not find a profile that is currently runnable with the detected hardware.

Plz advise.

2

Hi,

The “Could not find a profile that is currently runnable with the detected hardware.” error indicates that NIM can’t find a model profile to match the hardware you are running on.

Please check that your GPU drivers are up to date.

You can find the NIM profiles docs here Model Profiles — NVIDIA NIM for Large Language Models (LLMs).

Best,

Sophie