sortpoison

the question

Do llama.cpp's top_k, top_p, and min_p truncation samplers stay order-invariant under a stale sorted=true flag, and is that stale state reachable through the public sampler API?

what came out

No. Exhaustively over n! permutations with sorted forced true, top_p yields up to 11 distinct survivor sets, min_p 8, top_k 10, all wrong, while typical stays sound. logit_bias reorders logits without resetting sorted=false, so the public chain top_k to logit_bias to top_p keeps {0,1,2,3} where {3} is correct. The stock default chain is safe.

→ read the code and re-run it