Top k top p sampling from probs v262208
0 eligible runs
sampling
Top-k top-p (nucleus) sampling from probabilities with vocab_size=262208. Filters probabilities using top-k and top-p constraints, then samples from the filtered distribution. Captured from Gemma 3 27B.
Current records
No published measurement for the selected workload.
Implementations
Implementation
Runtime
Best latency
Evidence
Availability
Semantics
Inputs and outputs
probsfp32 [batch_size, vocab_size]
top_kint32 [batch_size]
top_pfp32 [batch_size]
samplesint64 [batch_size]
Axes and behavior
batch_sizevariable
vocab_sizeconstant = 262208
determinismunspecified
constraintsNo mutation or aliasing
Identity
No source imports for this operation yet.How records are decidedJSON