Argonne MI250 x1 llama.cpp meta-llama/Llama-2-7b-hf FP16 b64 128io
65.04 tok/s aggregate (batch*(in+out)/latency)
Fields
id
benchmarks/argonne-mi250-llamacpp-llama2-7b-fp16-1x-b64-128io-tpsMetric
tps_aggregate
Value
65.04
Unit
tok/s aggregate (batch*(in+out)/latency)
Model
meta-llama/Llama-2-7b-hf
Methodology
THIRD-PARTY MEASURED (Argonne LLM-Inference-Bench, arXiv:2411.00136, All_results.csv). llama.cpp on AMD MI250 x1 (Polaris node; MI250X silicon, filed as MI250), FP16, 128 in / 128 out, batch 64. Throughput = batch*(in+out)/latency = AGGREGATE across batch, NOT per-request decode. Latency 3.94s.
Measured by
third_party
Reproducible
yes
Thermal state
unknown
notes
Polaris node, 1x MI250. llama.cpp llama-bench-style throughput; batch-1 value approximates single-request decode.
Notes
Polaris node, 1x MI250. llama.cpp llama-bench-style throughput; batch-1 value approximates single-request decode.