MLPerf Inference v6.1: pioneering agent, VLM benchmarks

From the source: Lambda Blog

First agentic workload on datacenter hardware in MLPerf, and the first model over a trillion parameters. Plus 8.85% more throughput on identical hardware since v6.0.

Read the full story on Lambda Blog
Originally published by Lambda Blog on 17 Sept 2026. Techarda links to the original rather than republishing it. Read the full article →

Ask the square

The story is what was announced. If it raises a question for your team, ask the people who run this technology day to day. Your post links back to this story, so the next reader finds it too.

Recent threads in HPC & Accelerated Compute

Something wrong or out of date? Suggest a correction. We reply within 5 business days.

More from Lambda

Recent updates from Lambda, so you can tell whether this is a one-off or part of a pattern.

All Lambda news →

More in HPC & Accelerated Compute

What other companies in HPC & Accelerated Compute are doing. The category page shows who’s active, side by side.

Compare companies in HPC & Accelerated Compute →