RMSNorm 1024, batch one latency

Recorded result

Pass for the recorded test inputs. Median 79.552 us, p99 137.248 us over 20,000 calls

Recorded 2026-09-30

Execution conditions

• torch 2.10.0 with CUDA 12.8, driver 580.159.04
• 2,000 calls into fresh buffers gave 1 distinct output, a fresh process gave the same bits
• Signed card, Ed25519

Historical result; a new workload requires compatibility checking and fresh Verify.

Use this as your starting point

Save the reference, describe your workload and set the metric that matters. Your project keeps the selection and its recorded conditions together.

A historical result is not a compatibility guarantee. Your configuration needs a fresh Verify run.

Evidence summary imported from the local registry on October 2, 2026. A summary is not a newly issued proof pack.