Issue with llama-3.1:405b using https://console.runpod.io/hub/tanujdargan/runpod-worker-ollama
Hi I am stuck in a rollout in progress spinning wheel with no logs to see what is going on.
using this repo
https://console.runpod.io/hub/tanujdargan/runpod-worker-ollama
I have made the following mods
RUNPOD_INIT_TIMEOUT=800
OLLAMA_MODELS=/runpod-volume
gpuIds=BLACKWELL_96
gpuCount=4
locations=US-KS-2
networkVolumeId=exoXXredactedXX
I have two requests queued. But nothing is happening.
The network volume has 900Gb of space.
3 Replies