nemotron-3-super-nvfp4

vllmray@eugr

vLLM serving Nemotron-3-Super-120B using CUTLASS kernels

Quick Info

Runtimevllm (ray)

Tensor Parallel2

Nodes1+

Dtypenvfp4

Containervllm-node

Tensor Parallel (--tp)GPU Memory (--gpu-mem)Port (--port)Served Model Name

sparkrun run @eugr/nemotron-3-super-nvfp4