Module sampler 

Token sampling — temperature, top-p, top-k, min-p, repetition penalty.

Randomness comes from an explicit SplitMix64 PRNG carried by the caller: reproducible with a seed, unbiased across the whole CDF (the v1 subsec_nanos source could never pick past ~23% of it).

Structs

SamplerConfig

Sampling configuration.

SamplerScratch

Reusable per-pipeline sampling workspace. The epoch table lets the repetition penalty visit each token id once without allocating a HashSet or clearing a vocab-sized boolean vector on every decode step.

SplitMix64

SplitMix64 — tiny, fast, statistically solid for sampling.

Functions

argmax

Greedy: index of the maximum value.

sample

Sample next token from logits. Chain order is fixed: rep-penalty → temperature → softmax → min-p → top-k → top-p → sample.

sample_with_scratch

Sampling entry point for hot decode loops with reusable scratch storage.