this post was submitted on 26 Nov 2023
1 points (100.0% liked)

LocalLLaMA

3 readers
1 users here now

Community to discuss about Llama, the family of large language models created by Meta AI.

founded 1 year ago
MODERATORS
communick@poweruser.forum
1
Ollama slow running on high GPU Server - is the GPU not being utilized? (alien.top)
submitted 11 months ago by Smart-Egg-2568@alien.top to c/localllama@poweruser.forum
2 comments fedilink hide all child comments
 

Ollama-13B is running slowly on a cloud server that has a 32 GB Nvidia Tesla V100S. Do I need to changing my configuration to properly utilize the GPU memory?

top 2 comments
sorted by: hot top controversial new old
[–] campbe79@alien.top 1 points 11 months ago

What does nvidia-smi output?

[–] MultilogDumps@alien.top 1 points 11 months ago

Check nvidia-smi or install nvtop and check if the GPU is being utilised.