Model techniques map
Techniquesmodel architecturechannel mixermixture of expertsexpert load balancing

implementation detail · filed under model architecture

Histogram-based quantile estimation

Estimates expert quantiles from pooled histogram bin counts, combined across ranks with an all-reduce.

Also called Histogram estimation, B uniform bins.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 2

Documented in

Evidence

2 spans quoted from the sources, strongest treatment first.

We instead read each expert’s quantile from a histogram of its margins: a single all-reduce sums the per-rank bin counts, and the quantile is recovered from the pooled counts.

usedsoftware implementationin Kimi K3Moonshot AI

At the end of the step, a single all-reduce sums the local counts into the global histogram, and every rank recovers the quantile from the same pooled counts.

usedoptimizationin Kimi K3Moonshot AI

Filed alongside

Other methods under model architecture :: channel mixer :: mixture of experts :: expert load balancing.