NVIDIA : https://huggingface.co/nvidia/Qwen3.6-35B-A3B-NVFP4
Exemple :
models:
# Premier modèle : Llama 3 8B
- name: "meta-llama/Meta-Llama-3-8B-Instruct"
command: >
vllm serve meta-llama/Meta-Llama-3-8B-Instruct
--port 8001
--gpu-memory-utilization 0.85
ready_url: "http://127.0.0"
upstream_url: "http://127.0.0"
