Argonne MI300X vLLM Llama-3-70B b64
876.5 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi300x-vllm-llama3-70b-fp16-b64-128io-tpsMetric
tps_aggregate
Value
876.5
Unit
tok/s aggregate (batch*(in+out)/lat)
Model
meta-llama/Meta-Llama-3-70B
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136, All_results.csv). vLLM, FP16/BF16, 128in/128out, AGGREGATE over batch. 1x bs64 lat 18.69s. CSV 'AMD MI300X GPU' = 8x MI300X node (xGMI Infinity Fabric).
Measured by
third_party
Reproducible
yes