MoE expert computation with weighted accumulation
Complete MoE expert computation pipeline including expert selection, token routing to experts, parallel expert forward passes (SwiGLU MLPs), and weighted accumulation of expert outputs. This is the core computational bottleneck in MoE models.
Reported evidence · last observed 2026-08-17. Reported by source; not independently reproduced. No public source. License unknown.
Current records
Workloadsuite of 16 cases · mean latencyhidden_size = 2048 · num_experts = 128 · num_experts_per_tok = 8 · moe_intermediate_size = 76816 cases
Not measured on H100 for this workload. Challenges →
1373.4µs88% SOL1.00×Reported · license unknown · no source2026-08-17
Measured exactly what you asked. Reported by source; not independently reproduced.
2382.6µs88% SOL1.02×Reported · license unknown · no source2026-07-17
Measured exactly what you asked. Reported by source; not independently reproduced.
3389.6µs88% SOL1.04×Reported · license unknown · no source2026-08-20
Measured exactly what you asked. Reported by source; not independently reproduced.
4390.1µs87% SOL1.04×Reported · license unknown · no source2026-08-16
Measured exactly what you asked. Reported by source; not independently reproduced.
5393.3µs87% SOL1.05×Reported · license unknown · no source2026-08-18
Measured exactly what you asked. Reported by source; not independently reproduced.
6410.4µs86% SOL1.10×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
7417.4µs86% SOL1.12×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
8422.0µs87% SOL1.13×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
9506.9µs84% SOL1.36×Reported · license unknown · no source2026-07-16
Measured exactly what you asked. Reported by source; not independently reproduced.
10507.3µs84% SOL1.36×Reported · license unknown · no source2026-08-14
Measured exactly what you asked. Reported by source; not independently reproduced.
11531.8µs80% SOL1.42×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.
12582.8µs78% SOL1.56×Reported · license unknown · no source2026-08-07
Measured exactly what you asked. Reported by source; not independently reproduced.
131.03ms64% SOL2.77×Reported · license unknown · no source2026-07-27
Measured exactly what you asked. Reported by source; not independently reproduced.
141.53ms54% SOL4.11×Reported · license unknown · no source2026-07-10
Measured exactly what you asked. Reported by source; not independently reproduced.