openai-gpt-oss-120b

vllmtorch@eugr

vLLM serving openai/gpt-oss-120b with MXFP4 quantization and FlashInfer

Quick Info

Runtimevllm (torch)

Tensor Parallel1

Nodes1

Dtypemxfp4

Containervllm-node-mxfp4

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

sparkrun run @eugr/openai-gpt-oss-120b