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
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_tokenizer() const	tinyllama::TinyLlamaSession	inline
kv_cache_	tinyllama::TinyLlamaSession	private
max_batch_size_	tinyllama::TinyLlamaSession	private
model_	tinyllama::TinyLlamaSession	private
operator=(const TinyLlamaSession &)=delete	tinyllama::TinyLlamaSession	private
rng_	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
tokenizer_	tinyllama::TinyLlamaSession	private
use_batch_generation_	tinyllama::TinyLlamaSession	private
~TinyLlamaSession()	tinyllama::TinyLlamaSession