minimax-m2-awq

vllmray@eugr

vLLM serving MiniMax-M2-AWQ with Ray distributed backend

Quick Info

Runtimevllm (ray)

Tensor Parallel2

Nodes2+

Dtypeawq4

Containervllm-node

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

sparkrun run @eugr/minimax-m2-awq