Argonne GH200 x1 vLLM Llama-2-7B b64
8576.1 tok/s aggregate
Fields
id
benchmarks/argonne-gh200-vllm-llama2-7b-fp16-b64-128io-tpsMetric
tps_aggregate
Value
8,576.1
Unit
tok/s aggregate
Model
meta-llama/Llama-2-7b-hf
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136). vllm, FP16/BF16, 128in/128out. throughput=batch*(in+out)/e2e latency = AGGREGATE across batch. CSV 'Nvidia GH200 GPU' = GH200 Grace Hopper superchip (H100 GPU + Grace CPU over NVLink-C2C). Single-GPU rows only; the CSV has no multi-GPU GH200. bs64 lat 1.91s.
Measured by
third_party
Reproducible
yes
notes
GH200 superchip; on-package Grace CPU.
Notes
GH200 superchip; on-package Grace CPU.