The skills CLI now supports Notion hosted skills11m ago Palantir CEO Says AI Apocalypse Hype Is Mostly About Dodging Liability21m ago Our framework for reporting model misalignment22m ago Can Self-Driving Cars Give Spine Patients Their Independence Back?45m ago Iran Drone Strikes on Amazon Data Centers Are Permanently Deleting Customer Data46m ago Meta ordered to remove UK deepfakes as oversight board criticises ‘inadequate’ safeguards54m ago Base Labs launches an open-weight AI safety partnership with Hugging Face and Goodfire55m ago Pinterest teases a new ‘Restyle’ feature that lets you redesign your room with AI56m ago AI Changes Governance More Than It Changes Software1h ago Claude Code’s revised projects adds AI orchestration, but local developers must wait1h ago AI Agents Will Make Business Context an Operating Asset1h ago The critical vulnerability was a test database. That’s the whole triage problem.1h ago Building an Agent Harness for Life Sciences: Introducing Deep Life Sci1h ago AI needs to have 'reasonable guidelines,' Palantir's Karp tells CNBC1h ago

The skills CLI now supports Notion hosted skills11m ago Palantir CEO Says AI Apocalypse Hype Is Mostly About Dodging Liability21m ago Our framework for reporting model misalignment22m ago Can Self-Driving Cars Give Spine Patients Their Independence Back?45m ago Iran Drone Strikes on Amazon Data Centers Are Permanently Deleting Customer Data46m ago Meta ordered to remove UK deepfakes as oversight board criticises ‘inadequate’ safeguards54m ago Base Labs launches an open-weight AI safety partnership with Hugging Face and Goodfire55m ago Pinterest teases a new ‘Restyle’ feature that lets you redesign your room with AI56m ago AI Changes Governance More Than It Changes Software1h ago Claude Code’s revised projects adds AI orchestration, but local developers must wait1h ago AI Agents Will Make Business Context an Operating Asset1h ago The critical vulnerability was a test database. That’s the whole triage problem.1h ago Building an Agent Harness for Life Sciences: Introducing Deep Life Sci1h ago AI needs to have 'reasonable guidelines,' Palantir's Karp tells CNBC1h ago

Chips & Compute Machine Learning5 min reading time

NVIDIA Vera Rubin NVL72 Posts First MLPerf Inference Preview Results

Unite.AIPublished 1 day ago

NVIDIA announced its Vera Rubin NVL72 system's first MLPerf Inference v6.1 preview results, showing up to 3.7x higher throughput than its GB300 NVL72 system on the Qwen3-VL benchmark. The system also achieved 2.5x higher throughput on DeepSeek-R1, demonstrating significant performance improvements through hardware-software codesign.

#deepseek-r1 #inference-benchmarking #mlperf-inference #nvidia #qwen3-vl #vera-rubin-nvl72

More in Chips & Compute

Chips & Compute

Huawei Accelerates Launch of New AI Chip to Take On Nvidia

Covered by 2 sources19h ago

Chips & Compute

Huawei’s Plan to Become China’s Nvidia

The Wall Street Journal8h ago

Chips & Compute

The Startup That Built OpenAI’s Biggest Data Center Is Now Making Tiny Ones

The Wall Street Journal9h ago