Top k top p sampling from probs v152064
0 eligible runs
sampling
Top-k top-p (nucleus) sampling from probabilities with vocab_size=152064. Filters probabilities using top-k and top-p constraints, then samples from the filtered distribution. Captured from Qwen2.5 7B.
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 = 152064
determinismunspecified
constraintsNo mutation or aliasing
Identity
No source imports for this operation yet.How records are decidedJSON