Argonne LLM-Inference-Bench: SambaNova SN40L x8, SambaFlow, Llama-3-8B BF16, 128in/128out, batch 1
1165.7 tok/s aggregate (batch 1 single request on 8-RDU node)
Fields
id
benchmarks/argonne-sn40l-sambaflow-llama3-8b-8x-b1-128io-tpsMetric
tps_aggregate
Value
1,165.7
Unit
tok/s aggregate (batch 1 single request on 8-RDU node)
Model
meta-llama/Meta-Llama-3-8B
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench, arXiv:2411.00136, All_results.csv). FP16/BF16 weights, 128 in / 128 out. Throughput = batch*(in+out)/end-to-end latency = AGGREGATE over the batch, NOT per-request decode tok/s. Batch 1, 8x SN40L. Latency 0.220s.
Measured by
third_party
Reproducible
no