Argonne MI250 llama.cpp Llama-2-7B b64
65.0 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi250-llamacpp-llama2-7b-fp16-b64-128io-tpsMetric
tps_aggregate
Value
65
Unit
tok/s aggregate (batch*(in+out)/lat)
Model
meta-llama/Llama-2-7b-hf
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136, All_results.csv). llama.cpp, FP16/BF16, 128in/128out, AGGREGATE over batch. 1 tile bs64 lat 3.94s. CSV 'AMD MI250 GPU' = Polaris MI250.
Measured by
third_party
Reproducible
yes