Argonne LLM-Inference-Bench: Intel Max 1550 x1, vLLM 0.5.2-XPU, Llama-2-7B FP16, 128in/128out, batch 64
2100.9 tok/s aggregate across 64 batched requests
Fields
id
benchmarks/argonne-max1550-vllm-llama2-7b-fp16-b64-128io-tpsMetric
tps_aggregate
Value
2,100.9
Unit
tok/s aggregate across 64 batched requests
Model
meta-llama/Llama-2-7b-hf
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 64, 1x Max 1550. Latency 7.799s.
Measured by
third_party
Reproducible
yes