Argonne MI250 vLLM Qwen2-7B b1
136.0 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi250-vllm-qwen2-7b-fp16-b1-128io-tpsMetric
tps_aggregate
Value
136
Unit
tok/s aggregate (batch*(in+out)/lat)
Model
Qwen/Qwen2-7B
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136, All_results.csv). vLLM, FP16/BF16, 128in/128out, AGGREGATE over batch. 1 tile bs1 lat 1.88s. CSV 'AMD MI250 GPU' = Polaris MI250.
Measured by
third_party
Reproducible
yes