Mojo function

min_p_sampling

min_p_sampling[type: DType, out_idx_type: DType, //, _test_sort: Bool = False](min_ps: LayoutTensor[type, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], input_logits: LayoutTensor[type, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], out_token_ids: LayoutTensor[out_idx_type, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], temperature: SIMD[type, 1] = __init__[__mlir_type.!pop.int_literal](1))

Naive CPU implementation of Min-P sampling for token selection. This function applies temperature scaling, softmax, a merge sort, and then samples tokens based on the calculated probability threshold (Min-P).

Was this page helpful?

Thank you! We'll create more content like this.

Thank you for helping us improve!

😔 What went wrong?

Some code doesn’t work

It includes inaccurate information

It's missing information I need

It was difficult to understand

Other

Submit