mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-26 20:51:01 -05:00
* common : extract trie/ac to a separate file * common : support multiple token sequences in the reasoning budget sampler * common/trie : return matched word index * common/trie : rename "word" to "pattern" * common/reasoning-budget : expose matched end sequence * common/sampling : replay end sequence when reasoning budget is done * cont : update to use multiple end sequences * cont : clean up
81 KiB
81 KiB