Argonne MI250 vLLM Llama-3-70B 4x b64
1060.0 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi250-vllm-llama3-70b-fp16-4x-b64-128io-tpsMetric
tps_aggregate
Value
1,060
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. 4 tiles bs64 lat 15.46s. CSV 'AMD MI250 GPU' = Polaris MI250.
Measured by
third_party
Reproducible
yes