vllm serve /workspace/prisma/modelos/Qwen3.8-Flash-Next-FP8 --host 127.0.0.1 --port 8000 --served-model-name qwen3.8-flash-next --tensor-parallel-size 2 --max-model-len 32768 --gpu-memory-utilization 0.96 --enable-auto-tool-choice --tool-call-parser qwen3_xml --enforce-eager --max-num-seqs 4 --max-num-batched-tokens 4096 --reasoning-parser qwen3 --enable-log-requests --enable-log-outputs