CoreWeave Leads MLPerf 0.7 Endpoints Benchmark with DeepSeek-R1

From the source: CoreWeave Blog

CoreWeave posted the leading per-GPU DeepSeek-R1 throughput among NVIDIA GB200 NVL72 submissions in the inaugural MLPerf 0.7 Endpoints benchmark, tested on production infrastructure.

Read the full story on CoreWeave Blog
Originally published by CoreWeave Blog on 23 Oct 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 Cloud Infrastructure

Something wrong or out of date?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

More from CoreWeave

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

All CoreWeave news →

More in Cloud Infrastructure

What other companies in Cloud Infrastructure are doing. The category page shows who’s active, side by side.

Compare companies in Cloud Infrastructure →