Skip to main content

Python function

rejection_sampler_with_residuals

rejection_sampler_with_residuals()

max.pipelines.lib.rejection_sampler_with_residuals(device, *, seed=0, debug=False)

source

Builds a rejection sampler with residual sampling for speculative decoding.

Computes acceptance ratios for draft tokens, finds first rejection, samples from residual distribution (target - draft), and generates bonus tokens.

Parameters:

Return type:

Graph