MoE sparse routing and dispatch
Mixture of Experts sparse routing with top-2 expert selection from 64 experts, correction bias, weight normalization, token dispatch to expert MLPs with SiLU activation, and result aggregation. Includes shared expert computation.
Reported evidence · last observed 2026-08-16. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 9 cases · mean latencytop_k = 8 · hidden_size = 8192 · num_experts = 64 · intermediate_size = 3584 · shared_intermediate_size = 71689 cases
Not measured on H100 for this workload. Challenges →
15.74ms81% SOL1.00×Reported · license unknown · no source2026-08-16
Measured exactly what you asked. Reported by source; not independently reproduced.
25.83ms80% SOL1.02×Reported · license unknown · no source2026-07-16
Measured exactly what you asked. Reported by source; not independently reproduced.
35.93ms80% SOL1.03×Reported · license unknown · no source2026-07-17
Measured exactly what you asked. Reported by source; not independently reproduced.
46.09ms78% SOL1.06×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
56.10ms78% SOL1.06×Reported · license unknown · no source2026-08-11
Measured exactly what you asked. Reported by source; not independently reproduced.
66.11ms78% SOL1.06×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
76.18ms77% SOL1.08×Reported · license unknown · no source2026-08-16
Measured exactly what you asked. Reported by source; not independently reproduced.
86.19ms77% SOL1.08×Reported · license unknown · no source2026-07-30
Measured exactly what you asked. Reported by source; not independently reproduced.
96.20ms77% SOL1.08×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
106.32ms76% SOL1.10×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
116.39ms75% SOL1.11×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
127.58ms66% SOL1.32×Reported · license unknown · no source2026-07-11
Measured exactly what you asked. Reported by source; not independently reproduced.
1311.5ms47% SOL2.01×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
1411.8ms46% SOL2.06×Reported · license unknown · no source2026-07-24
Measured exactly what you asked. Reported by source; not independently reproduced.
1515.7ms36% SOL2.74×Reported · license unknown · no source2026-08-08
Measured exactly what you asked. Reported by source; not independently reproduced.
1616.3ms35% SOL2.83×Reported · license unknown · no source2026-07-28
Measured exactly what you asked. Reported by source; not independently reproduced.
1744.8ms14% SOL7.80×Reported · license unknown · no source2026-08-10
Measured exactly what you asked. Reported by source; not independently reproduced.