RMSNorm h2048
Root Mean Square Normalization with hidden_size=2048. Captured from Qwen3-30B-A3B. Epsilon is fixed at 1e-6.
Reported evidence · last observed 2026-07-23. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 7 cases · mean latency14 cases
Not measured on H100 for this workload. Challenges →
14.07µs77% SOL1.00×Reported · license unknown · no source2026-07-23
Measured exactly what you asked. Reported by source; not independently reproduced.
24.10µs76% SOL1.01×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
34.14µs76% SOL1.02×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
3=4.14µs76% SOL1.02×Reported · license unknown · no source2026-07-31
Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.
44.15µs76% SOL1.02×Reported · license unknown · no source2026-07-22
Measured exactly what you asked. Reported by source; not independently reproduced.
54.15µs77% SOL1.02×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
64.17µs77% SOL1.02×Reported · license unknown · no source2026-08-20
Measured exactly what you asked. Reported by source; not independently reproduced.
74.22µs77% SOL1.04×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
84.22µs76% SOL1.04×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
94.26µs76% SOL1.05×Reported · license unknown · no source2026-08-19
Measured exactly what you asked. Reported by source; not independently reproduced.
104.26µs76% SOL1.05×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
114.27µs75% SOL1.05×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
124.32µs75% SOL1.06×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
134.34µs76% SOL1.07×Reported · license unknown · no source2026-08-03
Measured exactly what you asked. Reported by source; not independently reproduced.
144.35µs74% SOL1.07×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
14=4.35µs75% SOL1.07×Reported · license unknown · no source2026-07-10
Measured exactly what you asked; tied ranks share a number. Reported by source; not independently reproduced.
154.41µs74% SOL1.08×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
164.52µs74% SOL1.11×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
174.55µs74% SOL1.12×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
184.65µs73% SOL1.14×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
194.67µs72% SOL1.15×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
204.67µs73% SOL1.15×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
214.70µs72% SOL1.15×Reported · license unknown · no source2026-07-29
Measured exactly what you asked. Reported by source; not independently reproduced.
224.91µs71% SOL1.20×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
234.92µs72% SOL1.21×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
244.94µs71% SOL1.21×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
255.03µs71% SOL1.24×Reported · license unknown · no source2026-07-19
Measured exactly what you asked. Reported by source; not independently reproduced.
265.33µs68% SOL1.31×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
275.62µs67% SOL1.38×Reported · license unknown · no source2026-07-18
Measured exactly what you asked. Reported by source; not independently reproduced.
286.11µs62% SOL1.50×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
296.37µs61% SOL1.56×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
307.51µs58% SOL1.84×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
Implementations
Show all 52 implementations ›Showing all 52 implementations ⌄
Semantics
Also indexed as 024-rmsnorm-h2048 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.