Argonne MI300X llama.cpp Llama-3-70B b1
15.4 tok/s aggregate (batch*(in+out)/lat)
Fields
id
benchmarks/argonne-mi300x-llamacpp-llama3-70b-fp16-b1-128io-tpsMetric
tps_aggregate
Value
15.4
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). llama.cpp, FP16/BF16, 128in/128out, AGGREGATE over batch. 1x bs1 lat 16.61s. CSV 'AMD MI300X GPU' = 8x MI300X node (xGMI Infinity Fabric).
Measured by
third_party
Reproducible
yes