inference/research
verifiedhigh · 0.90updated 2026-10-04

MLPerf v6.1 CoreWeave GB200 NVL72 (72x GB200-186GB aarch64) llama2-70b-99.9 Offline run_1 harness summary log

benchmark

Fields

id
sources/bench-mlperf-v6-1-coreweave-gb200-nvl72-llama2-offline-log
URL
https://raw.githubusercontent.com/mlcommons/inference_results_v6.1/main/closed/CoreWeave/results/GB200-NVL72_GB200-186GB_aarch64x72_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 3292.1, Tokens per second 894002. Whole-rack: 72 GB200 GPUs across 18 nodes (4 per node).

Notes

Result is : VALID. Samples per second 3292.1, Tokens per second 894002. Whole-rack: 72 GB200 GPUs across 18 nodes (4 per node).

Cross-references

This record references no other records.