Argonne SN40L x8 SambaFlow Llama-3-8B b16
7381.3 tok/s aggregate
Fields
id
benchmarks/argonne-sn40l-sambaflow-llama3-8b-8x-b16-128io-tpsMetric
tps_aggregate
Value
7,381.3
Unit
tok/s aggregate
Model
meta-llama/Meta-Llama-3-8B
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench arXiv:2411.00136, All_results.csv). sambaflow-sambanova-rdu-runtime, FP16/BF16, 128in/128out, AGGREGATE over batch. 8x SN40L bs16.
Measured by
third_party
Reproducible
yes
notes
Multi-accelerator count noted in methodology.
Notes
Multi-accelerator count noted in methodology.