deepseek-ai / DeepSeek-MoE

DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
MIT License
982 stars 48 forks source link

CUDA error: device-side assert triggered when trying to run the model #4

Closed intervitens closed 9 months ago

intervitens commented 9 months ago

Error log: https://sprunge.us/MefNDs Example I'm trying to run: http://sprunge.us/laQn8Q Installed packages and versions: http://sprunge.us/ich59c The only thing I changed from the example in the HF repo is the device map to prevent OOM on my dual GPU setup.

EDIT: seems to be some kind of an issue with my OS/hardware, cannot replicate on a rented machine.

intervitens commented 9 months ago

Closing issue, since this doesn't seem to be related to the model itself.

intervitens commented 9 months ago

Downgrading the NVIDIA driver from version 545 to 535 solved the issue.