tinyllama::TinyLlamaSession Member List

This is the complete list of members for tinyllama::TinyLlamaSession, including all inherited members.

batch_generation_parallel(const std::vector< int > &current_tokens, const std::vector< int > &token_positions, const std::vector< int > &original_sequence_indices, std::vector< std::vector< float > > &batch_logits)	tinyllama::TinyLlamaSession	private
batch_prefill_parallel(const std::vector< std::vector< int > > &all_tokens, const std::vector< int > &prompt_lengths, std::vector< std::vector< float > > &batch_final_logits)	tinyllama::TinyLlamaSession	private
bpe_	tinyllama::TinyLlamaSession	private
bpe_decode(const std::vector< int > &ids) const	tinyllama::TinyLlamaSession	inline
bpe_encode(const std::string &text) const	tinyllama::TinyLlamaSession	inline
bpe_prompt_ids(const std::string &text) const	tinyllama::TinyLlamaSession	inline
bpe_token_count(const std::string &text) const	tinyllama::TinyLlamaSession	inline
chat_format() const	tinyllama::TinyLlamaSession	inline
chat_template() const	tinyllama::TinyLlamaSession	inline
chat_template_why() const	tinyllama::TinyLlamaSession	inline
chat_template_why_	tinyllama::TinyLlamaSession	private
config_	tinyllama::TinyLlamaSession	private
eos_token_id_	tinyllama::TinyLlamaSession	private
generate(const std::string &prompt, int steps=128, float temperature=0.1f, int top_k=40, float top_p=0.9f, const std::string &system_prompt="", bool apply_q_a_format=false)	tinyllama::TinyLlamaSession
generate_batch(const std::vector< std::string > &prompts, int steps=128, float temperature=0.1f, int top_k=40, float top_p=0.9f, const std::string &system_prompt="", bool apply_q_a_format=false)	tinyllama::TinyLlamaSession
generated_stream_	tinyllama::TinyLlamaSession	private
generated_text_for_api_return_	tinyllama::TinyLlamaSession	private
get_config() const	tinyllama::TinyLlamaSession	inline
get_kv_cache()	tinyllama::TinyLlamaSession	inline
get_repetition_penalty() const	tinyllama::TinyLlamaSession	inline
get_tokenizer() const	tinyllama::TinyLlamaSession	inline
gguf_tokens() const	tinyllama::TinyLlamaSession
ir_	tinyllama::TinyLlamaSession	private
ir_doc_	tinyllama::TinyLlamaSession	private
ir_document() const	tinyllama::TinyLlamaSession	inline
is_bpe() const	tinyllama::TinyLlamaSession	inline
is_chat_eos(int id) const	tinyllama::TinyLlamaSession	inline
is_chat_stop(int id) const	tinyllama::TinyLlamaSession	inline
kv_cache_	tinyllama::TinyLlamaSession	private
kv_token_history_	tinyllama::TinyLlamaSession	private
last_generated_ids() const	tinyllama::TinyLlamaSession	inline
last_generated_ids_	tinyllama::TinyLlamaSession	private
last_generated_tokens() const	tinyllama::TinyLlamaSession	inline
last_generated_tokens_	tinyllama::TinyLlamaSession	private
last_prompt_ids() const	tinyllama::TinyLlamaSession	inline
last_prompt_ids_	tinyllama::TinyLlamaSession	private
last_stop_id() const	tinyllama::TinyLlamaSession	inline
last_stop_id_	tinyllama::TinyLlamaSession	private
last_stop_reason() const	tinyllama::TinyLlamaSession	inline
last_stop_reason_	tinyllama::TinyLlamaSession	private
last_ttft() const	tinyllama::TinyLlamaSession	inline
last_ttft_	tinyllama::TinyLlamaSession	private
max_batch_size_	tinyllama::TinyLlamaSession	private
model_	tinyllama::TinyLlamaSession	private
operator=(const TinyLlamaSession &)=delete	tinyllama::TinyLlamaSession	private
repeat_last_n_	tinyllama::TinyLlamaSession	private
repeat_penalty_	tinyllama::TinyLlamaSession	private
repetition_penalty_	tinyllama::TinyLlamaSession	private
rng_	tinyllama::TinyLlamaSession	private
sample_step(std::vector< float > &logits, const std::vector< int > &context, float temperature, int top_k, float top_p)	tinyllama::TinyLlamaSession
score_context() const	tinyllama::TinyLlamaSession
score_ids_	tinyllama::TinyLlamaSession	private
score_reuse_ok() const	tinyllama::TinyLlamaSession
score_rows(const std::vector< int > &ids, int first_row, bool reuse_prefix, int *reused=nullptr)	tinyllama::TinyLlamaSession
score_vocab() const	tinyllama::TinyLlamaSession
scripted_replies_	tinyllama::TinyLlamaSession	private
set_repeat_penalty(float p, int last_n)	tinyllama::TinyLlamaSession	inline
set_repetition_penalty(float p)	tinyllama::TinyLlamaSession	inline
set_scripted_replies(std::vector< std::vector< int > > r)	tinyllama::TinyLlamaSession	inline
set_seed(unsigned seed)	tinyllama::TinyLlamaSession	inline
set_token_callback(std::function< void(int)> cb)	tinyllama::TinyLlamaSession	inline
state_k() const	tinyllama::TinyLlamaSession	inline
state_k_	tinyllama::TinyLlamaSession	private
state_vocab_	tinyllama::TinyLlamaSession	private
threads_	tinyllama::TinyLlamaSession	private
TinyLlamaSession(const std::string &model_path, const std::string &tokenizer_path, int threads=1, int num_gpu_layers_from_cli=0, bool cli_use_mmap=true, bool use_kv_quant=false, bool use_batch_generation=false, int max_batch_size=1)	tinyllama::TinyLlamaSession
TinyLlamaSession(const TinyLlamaSession &)=delete	tinyllama::TinyLlamaSession	private
token_callback_	tinyllama::TinyLlamaSession	private
tokenizer_	tinyllama::TinyLlamaSession	private
use_batch_generation_	tinyllama::TinyLlamaSession	private
word_template_	tinyllama::TinyLlamaSession	private
~TinyLlamaSession()	tinyllama::TinyLlamaSession