vllm
vllm copied to clipboard
[Feature]: Build and publish Neuron docker image
🚀 The feature, motivation and pitch
It seems like the current docker images don't support Neuron (Inferentia). It would be very helpful if there was a tested, managed Neuron docker image to use. While at the same subject, it would be even better if some documentation would be added on running vLlm Neuron using containers.
Alternatives
DJL?
Additional context
No response