For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).

Mojo function

topp_minp_sampling_kernel

def topp_minp_sampling_kernel[dtype: DType, out_idx_type: DType, is_top_p: Bool](p_thresholds_: Pointer[Scalar[dtype], MutUntrackedOrigin], sorted_probs_: Pointer[Scalar[dtype], MutUntrackedOrigin], sorted_ids_: Pointer[Scalar[out_idx_type], MutUntrackedOrigin], out_token_ids: Pointer[Scalar[out_idx_type], MutUntrackedOrigin], skip_sort: Pointer[Scalar[DType.bool], MutUntrackedOrigin], vocab_size: Int32)

Top P-Min P sampling kernel.

Parameters:

• ​dtype (DType): DType - scalar values dtype.
• ​out_idx_type (DType): DType - output index type.
• ​is_top_p (Bool): Bool - Whether to use Top-P (True) or Min-P (False) sampling.