RMSNorm h7168
Root Mean Square Normalization with hidden_size=7168. Captured from DeepSeek-V3/R1. Epsilon is fixed at 1e-6.
Reported evidence · last observed 2026-07-30. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 8 cases · mean latency16 cases
Not measured on H100 for this workload. Challenges →
16.15µs83% SOL1.00×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
26.15µs83% SOL1.00×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
36.20µs82% SOL1.01×Reported · license unknown · no source2026-07-23
Measured exactly what you asked. Reported by source; not independently reproduced.
46.25µs82% SOL1.02×Reported · license unknown · no source2026-07-22
Measured exactly what you asked. Reported by source; not independently reproduced.
56.27µs84% SOL1.02×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
66.28µs84% SOL1.02×Reported · license unknown · no source2026-08-21
Measured exactly what you asked. Reported by source; not independently reproduced.
76.31µs84% SOL1.03×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
86.34µs83% SOL1.03×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
96.43µs83% SOL1.05×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
106.48µs83% SOL1.05×Reported · license unknown · no source2026-07-31
Measured exactly what you asked. Reported by source; not independently reproduced.
116.51µs83% SOL1.06×Reported · license unknown · no source2026-08-02
Measured exactly what you asked. Reported by source; not independently reproduced.
126.55µs83% SOL1.07×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
136.57µs84% SOL1.07×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
146.64µs82% SOL1.08×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
156.76µs82% SOL1.10×Reported · license unknown · no source2026-07-29
Measured exactly what you asked. Reported by source; not independently reproduced.
166.93µs80% SOL1.13×Reported · license unknown · no source2026-08-01
Measured exactly what you asked. Reported by source; not independently reproduced.
177.07µs81% SOL1.15×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
187.15µs81% SOL1.16×Reported · license unknown · no source2026-07-26
Measured exactly what you asked. Reported by source; not independently reproduced.
197.23µs80% SOL1.18×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
207.27µs80% SOL1.18×Reported · license unknown · no source2026-07-18
Measured exactly what you asked. Reported by source; not independently reproduced.
217.32µs81% SOL1.19×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
227.33µs78% SOL1.19×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
237.43µs79% SOL1.21×Reported · license unknown · no source2026-07-20
Measured exactly what you asked. Reported by source; not independently reproduced.
247.54µs78% SOL1.23×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
257.59µs79% SOL1.24×Reported · license unknown · no source2026-08-03
Measured exactly what you asked. Reported by source; not independently reproduced.
267.87µs79% SOL1.28×Reported · license unknown · no source2026-08-03
Measured exactly what you asked. Reported by source; not independently reproduced.
278.26µs75% SOL1.34×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
288.46µs74% SOL1.38×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
299.07µs75% SOL1.48×Reported · license unknown · no source2026-08-11
Measured exactly what you asked. Reported by source; not independently reproduced.
309.48µs73% SOL1.54×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
3111.1µs64% SOL1.81×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
3211.5µs66% SOL1.88×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
3316.1µs55% SOL2.61×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.
Implementations
Show all 56 implementations ›Showing all 56 implementations ⌄
Semantics
Also indexed as rmsnorm-h7168 · reviewed as the same computation; every definition's cohorts are shown here, ranked separately.