NVIDIA HGX H100 8-GPU

配置

部署案例 (3)

• DeepSeek V4 Flash on 8×H100 SXM with vLLM FP8
  deepseek-v4-flash · vllm · fp8-e4m3 · decode 4200 tok/s
• Llama 4 Scout on 8×H100 SXM with vLLM (public benchmark)
  llama-4-scout · vllm · bf16 · decode 1850 tok/s
• Gemma 4 26B on 4× H100 SXM with FP8
  gemma-4 · tensorrt-llm · fp8-e4m3 · decode 6800 tok/s

引证

1. [1] NVIDIA HGX H100 system specs — https://www.nvidia.com/en-us/data-center/hgx/ 📄厂商声称