45 const std::string& text,
bool add_special)
const override;
47 std::string
detokenize(int32_t token)
const override;
50 const llama_vocab* vocab_;
Tokenizer adapter that forwards to llama.cpp's vocab API.
std::string detokenize(int32_t token) const override
Decode a single token id to its surface string.
std::vector< int32_t > tokenize(const std::string &text, bool add_special) const override
Encode text into token ids via the wrapped vocab.
Pure-virtual tokenizer surface used by the inference backend.
Activate model on GPU (WARM → ACTIVE).
Abstract Tokenizer seam for backend testability (v2.3.10).