Add vllm config and information
#11
by radekosmulski-nvidia - opened
No description provided.
ybabakhin changed pull request status to merged
@radekosmulski-nvidia I am trying to follow the instructions with the vLLM images from NGC and I keep getting issues when trying to serve the model with vLLM https://forums.developer.nvidia.com/t/getting-nemotron-embed-working-on-dgx-spark/359447/2
Do the instructions need to be updated?