MLPerf Inference v4.0 — ASUSTeK ESC8000_E11 8x NVIDIA L4, BERT-99/99.9, TensorRT

Fields

id

sources/bench-mlperf-v4-0-asustek-8xl4-bert99

URL

https://github.com/mlcommons/inference_results_v4.0/tree/main/closed/ASUSTeK/results/ESC8000_E11_L4x8_TRT

Publisher

MLCommons / ASUSTeK

Kind

benchmark

Accessed

2026-10-14

notes

Closed-division submission. 8x NVIDIA L4-PCIe-24GB, TensorRT, BERT-large (bert-99 and bert-99.9), Offline + Server scenarios. 'Samples per second' verbatim from mlperf_log_summary.txt. Aggregate across 8 cards.

Notes

Closed-division submission. 8x NVIDIA L4-PCIe-24GB, TensorRT, BERT-large (bert-99 and bert-99.9), Offline + Server scenarios. 'Samples per second' verbatim from mlperf_log_summary.txt. Aggregate across 8 cards.

Cross-references

This record references no other records.