inference/research
verifiedlow · 0.50updated 2026-10-14

MLPerf Inference v4.1 — Cisco C245M8 2x H100 PCIe 80GB, GPT-J 99%, TensorRT

benchmark

Fields

id
sources/bench-mlperf-v4-1-cisco-h100pcie-gptj
URL
https://github.com/mlcommons/inference_results_v4.1/tree/main/closed/Cisco/results/C245M8_H100_PCIe_80GBx2_TRT
Publisher
MLCommons / Cisco
Kind
benchmark
Accessed
2026-10-14
notes
Raw submission logs. TensorRT, GPT-J 6B, Offline scenario. Tokens/sec (inferred) verbatim from mlperf_log_summary.txt.

Notes

Raw submission logs. TensorRT, GPT-J 6B, Offline scenario. Tokens/sec (inferred) verbatim from mlperf_log_summary.txt.

Cross-references

This record references no other records.