MLPerf v6.1 NVIDIA DGX B300 (8x B300-SXM-270GB) llama2-70b-99.9 Offline run_1 harness summary log

Fields

id

sources/bench-mlperf-v6-1-nvidia-b300-llama2-offline-log

URL

https://raw.githubusercontent.com/mlcommons/inference_results_v6.1/main/closed/NVIDIA/results/B300-SXM-270GBx8_TRT/llama2-70b-99.9/Offline/performance/run_1/mlperf_log_summary.txt

Publisher

MLCommons

Kind

benchmark

Accessed

2026-10-04

notes

Result is : VALID. Samples per second 400.205, Tokens per second 109277. Min duration satisfied: Yes, Min queries satisfied: Yes, Early stopping satisfied: Yes. Offline imposes no latency constraint at all - the log records latency percentiles (mean 670.3 s per sample) but no 'Performance constraints satisfied' line, because there is nothing to satisfy. This is the structural difference from Server visible directly in the log.

Notes

Result is : VALID. Samples per second 400.205, Tokens per second 109277. Min duration satisfied: Yes, Min queries satisfied: Yes, Early stopping satisfied: Yes. Offline imposes no latency constraint at all - the log records latency percentiles (mean 670.3 s per sample) but no 'Performance constraints satisfied' line, because there is nothing to satisfy. This is the structural difference from Server visible directly in the log.

Cross-references

This record references no other records.