MLPerf v6.1 Dell XE9785L 8xMI355X llama3.1-8b Interactive run_1 harness summary log

Fields

id

sources/bench-mlperf-v6-1-dell-mi355x-llama3-8b-interactive-log

URL

https://raw.githubusercontent.com/mlcommons/inference_results_v6.1/main/closed/Dell/results/XE9785L_8xMI355X/llama3.1-8b/Interactive/performance/run_1/mlperf_log_summary.txt

Publisher

MLCommons

Kind

benchmark

Accessed

2026-10-04

notes

Result is : VALID, Completed samples per second 1019.06, Completed tokens per second 130539.57 - and the header again reads 'Scenario : Server'. Same Interactive-labelling defect as the AMD artifact. On this node Interactive (130540) sits BELOW Server (148563) by 12%, which is the direction one expects once inter-token latency is hard-capped.

Notes

Result is : VALID, Completed samples per second 1019.06, Completed tokens per second 130539.57 - and the header again reads 'Scenario : Server'. Same Interactive-labelling defect as the AMD artifact. On this node Interactive (130540) sits BELOW Server (148563) by 12%, which is the direction one expects once inter-token latency is hard-capped.

Cross-references

This record references no other records.