23 lines
457 B
ReStructuredText
23 lines
457 B
ReStructuredText
.. _apisampling:
|
|
|
|
flashinfer.sampling
|
|
===================
|
|
|
|
Kernels for LLM sampling.
|
|
|
|
.. currentmodule:: flashinfer.sampling
|
|
|
|
.. autosummary::
|
|
:toctree: ../generated
|
|
|
|
sampling_from_probs
|
|
top_p_sampling_from_probs
|
|
top_k_sampling_from_probs
|
|
min_p_sampling_from_probs
|
|
top_k_top_p_sampling_from_logits
|
|
top_k_top_p_sampling_from_probs
|
|
top_p_renorm_probs
|
|
top_k_renorm_probs
|
|
top_k_mask_logits
|
|
chain_speculative_sampling
|