Code
Hub
Workspaces
Following
Trending
Connect
MCP
copy
Create free account
hub
/
github.com/abetlen/llama-cpp-python
/ functions
Functions
1,336 in github.com/abetlen/llama-cpp-python
⨍
Functions
1,336
◇
Types & classes
256
↳
Endpoints
95
↓ 1 callers
Method
save_sequence_state_bytes
(self, seq_id: int)
examples/server/server.py:13254
↓ 1 callers
Method
selected_completions
(self)
examples/server/server.py:4248
↓ 1 callers
Method
sequence_cache_metric_definitions
( self, )
examples/server/server.py:15019
↓ 1 callers
Method
set_draft_processing_enabled
(self, enabled: bool)
examples/server/server.py:12176
↓ 1 callers
Function
set_llama_proxy
(model_settings: List[ModelSettings])
llama_cpp/server/app.py:68
↓ 1 callers
Function
set_ping_message_factory
(factory: typing.Callable[[], bytes])
llama_cpp/server/app.py:95
↓ 1 callers
Function
set_server_settings
(server_settings: ServerSettings)
llama_cpp/server/app.py:53
↓ 1 callers
Method
set_target_processing_enabled
(self, enabled: bool)
examples/server/server.py:1201
↓ 1 callers
Function
set_verbose
(verbose: bool)
llama_cpp/_logger.py:49
↓ 1 callers
Method
speculative_metric_definitions
( self, )
examples/server/server.py:15061
↓ 1 callers
Method
step
(self)
examples/server/server.py:13363
↓ 1 callers
Method
stream_completion_chunks
( self, request: CompletionRequest, completion: Completion, finish_reason: Opt
examples/server/server.py:10078
↓ 1 callers
Function
stream_sse_outputs
( formatter: OpenAIFormatter, http_request: Request, stream: CompletionStream,
examples/server/server.py:15866
↓ 1 callers
Function
stream_websocket_responses
( websocket: WebSocket, formatter: OpenAIFormatter, stream: CompletionStream,
examples/server/server.py:15911
↓ 1 callers
Method
text_token_at
(self, pos: int)
examples/server/server.py:4021
↓ 1 callers
Method
to_chat_handler
(self)
llama_cpp/llama_chat_format.py:302
↓ 1 callers
Method
to_chat_response_format
(self)
examples/server/server.py:3064
↓ 1 callers
Method
to_chat_template_tool_choice
(self)
examples/server/server.py:3033
↓ 1 callers
Method
to_create_response_request
(self)
examples/server/server.py:3134
↓ 1 callers
Method
to_gbnf
(cls, schema: str, prop_order: Optional[List[str]] = None)
examples/server/server.py:771
↓ 1 callers
Method
to_template_response_format
(self)
examples/server/server.py:2855
↓ 1 callers
Method
to_template_tool_choice
(self)
examples/server/server.py:2820
↓ 1 callers
Method
token_bos
(self)
llama_cpp/_internals.py:133
↓ 1 callers
Method
token_bytes
(self, token: int)
examples/server/server.py:12062
↓ 1 callers
Method
token_cls
(self)
llama_cpp/_internals.py:139
↓ 1 callers
Method
token_sep
(self)
llama_cpp/_internals.py:142
↓ 1 callers
Method
tokenize
( self, text: bytes, add_bos: bool = True, special: bool = True )
llama_cpp/llama_tokenizer.py:49
↓ 1 callers
Method
truncate_free_sequence
(self, seq_id: int, keep_len: int)
examples/server/server.py:14943
↓ 1 callers
Method
truncate_sequence_metadata
( self, seq_id: int, current_len: int, keep_len: int, )
examples/server/server.py:14933
↓ 1 callers
Function
websocket_request_with_ephemeral_history
( ws_body: ResponseCreateWebSocketRequest, )
examples/server/server.py:16185
Method
__call__
( self, input_ids: npt.NDArray[np.intc], /, **kwargs: Any )
llama_cpp/llama_speculative.py:11
Method
__call__
( self, input_ids: npt.NDArray[np.intc], /, **kwargs: Any )
llama_cpp/llama_speculative.py:57
Method
__call__
Generate text from a prompt. Args: prompt: The prompt to generate text from. suffix: A suffix to append to the genera
llama_cpp/llama.py:1905
Method
__call__
( self, input_ids: npt.NDArray[np.intc], scores: npt.NDArray[np.single] )
llama_cpp/llama.py:2474
Method
__call__
( self, input_ids: npt.NDArray[np.intc], logits: npt.NDArray[np.single] )
llama_cpp/llama.py:2486
Method
__call__
( self, input_ids: npt.NDArray[np.intc], scores: npt.NDArray[np.single] )
llama_cpp/llama.py:2498
Method
__call__
( self, *, # llama.cpp instance llama: llama.Llama, # openai api param
llama_cpp/llama_chat_format.py:69
Method
__call__
( self, *, messages: List[llama_types.ChatCompletionRequestMessage], functions
llama_cpp/llama_chat_format.py:258
Method
__call__
( self, *, llama: llama.Llama, messages: List[llama_types.ChatCompletionReques
llama_cpp/llama_chat_format.py:2852
Method
__call__
( self, *, llama: llama.Llama, messages: List[llama_types.ChatCompletionReques
llama_cpp/llama_chat_format.py:3402
Method
__call__
(self, **kwargs)
llama_cpp/llama_chat_format.py:4102
Method
__call__
(cls, *args: Any, **kwargs: Any)
llama_cpp/_utils.py:87
Method
__call__
(self, model: Optional[str] = None)
llama_cpp/server/model.py:36
Method
__call__
(self, http_request: Request)
examples/ray/llm.py:13
Method
__call__
(self, char)
examples/low_level_api/util.py:18
Method
__contains__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:39
Method
__contains__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:88
Method
__contains__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:141
Method
__del__
(self)
llama_cpp/llama.py:2284
Method
__del__
(self)
llama_cpp/_internals.py:88
Method
__del__
(self)
llama_cpp/_internals.py:283
Method
__del__
(self)
llama_cpp/_internals.py:496
Method
__del__
(self)
llama_cpp/_internals.py:695
Method
__enter__
(self)
llama_cpp/_utils.py:24
Method
__enter__
(self)
examples/low_level_api/low_level_api_chat_cpp.py:628
Method
__exit__
(self, *_)
llama_cpp/_utils.py:60
Method
__exit__
(self, type, value, tb)
examples/low_level_api/low_level_api_chat_cpp.py:631
Method
__getitem__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:35
Method
__getitem__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:79
Method
__getitem__
(self, key: Sequence[int])
llama_cpp/llama_cache.py:130
Method
__getitem__
(self, model: str)
llama_cpp/server/model.py:56
Method
__getitem__
(self, val)
examples/low_level_api/util.py:46
Method
__getstate__
(self)
llama_cpp/llama.py:2136
Method
__init__
(self, max_ngram_size: int = 2, num_pred_tokens: int = 10)
llama_cpp/llama_speculative.py:20
Method
__init__
( self, input_ids: npt.NDArray[np.intc], scores: npt.NDArray[np.single], n_tok
llama_cpp/llama.py:2451
Method
__init__
(self, min_tokens: int, token_eos: int)
llama_cpp/llama.py:2493
Method
__init__
(self, llama: llama_cpp.Llama)
llama_cpp/llama_tokenizer.py:46
Method
__init__
(self, hf_tokenizer: Any)
llama_cpp/llama_tokenizer.py:78
Method
__init__
(self, capacity_bytes: int = (2 << 30))
llama_cpp/llama_cache.py:20
Method
__init__
( self, cache_dir: str = ".cache/llama_cache", capacity_bytes: int = (2 << 30) )
llama_cpp/llama_cache.py:107
Method
__init__
(self, *args, _grammar: str, **kwargs)
llama_cpp/llama_grammar.py:20
Method
__init__
(self, content: str, deps: list = None)
llama_cpp/llama_grammar.py:311
Method
__init__
(self, *, prop_order, allow_fetch, dotall, raw_pattern)
llama_cpp/llama_grammar.py:381
Method
__init__
A chat formatter that uses jinja2 templates to format the prompt.
llama_cpp/llama_chat_format.py:205
Method
__init__
(self, clip_model_path: str, verbose: bool = True)
llama_cpp/llama_chat_format.py:2776
Method
__init__
( self, clip_model_path: str, verbose: bool = True, use_gpu: bool = True )
llama_cpp/llama_chat_format.py:3270
Method
__init__
( self, *, path_model: str, params: llama_cpp.llama_model_params, verb
llama_cpp/_internals.py:36
Method
__init__
( self, *, model: LlamaModel, params: llama_cpp.llama_context_params,
llama_cpp/_internals.py:251
Method
__init__
( self, *, n_tokens: int, embd: int, n_seq_max: int, verbose: bool = True )
llama_cpp/_internals.py:468
Method
__init__
(self, *, n_vocab: int)
llama_cpp/_internals.py:531
Method
__init__
(self, apply_func: Callable[[llama_cpp.llama_token_data_array], None])
llama_cpp/_internals.py:645
Method
__init__
(self)
llama_cpp/_internals.py:676
Method
__init__
(self, disable: bool = True)
llama_cpp/_utils.py:20
Method
__init__
(self)
llama_cpp/_utils.py:98
Method
__init__
(self, models: List[ModelSettings])
llama_cpp/server/model.py:15
Method
__init__
(self, model_path: str, **kwargs: Any)
examples/high_level_api/langchain_custom_llm.py:17
Method
__init__
(self, model_path: str)
examples/ray/llm.py:10
Method
__init__
( self, *, prop_order: Dict[str, int], allow_fetch: bool, dotall: bool
examples/server/server.py:291
Method
__init__
(self)
examples/server/server.py:797
Method
__init__
(self)
examples/server/server.py:1039
Method
__init__
(self, max_ngram_size: int = 2, num_pred_tokens: int = 10)
examples/server/server.py:1209
Method
__init__
( self, *, model: "Model", draft_model: Any, context_params: Any,
examples/server/server.py:1261
Method
__init__
(self, template: str, *, bos_token: str, eos_token: str)
examples/server/server.py:3484
Method
__init__
( self, schema: Dict[str, Any], *, tools: Optional[List[ChatTemplateTool]] = N
examples/server/server.py:4398
Method
__init__
(self, model: Model)
examples/server/server.py:7847
Method
__init__
( self, *, seed: int, vocab: llama_cpp.llama_vocab_p, n_vocab: int,
examples/server/server.py:10265
Method
__init__
( self, *, path: str, max_bytes: int, model_fingerprint: str,
examples/server/server.py:10397
Method
__init__
( self, *, model_path: str, llama_model: Any, chat_formatter: Jinja2Ch
examples/server/server.py:10550
Method
__init__
( self, *, model_path: str, model_alias: Optional[str] = None, chat_te
examples/server/server.py:11235
Method
__init__
( self, *, path: Union[str, Path], max_bytes: int, compatibility_key:
examples/server/server.py:12334
← previous
next →
601–700 of 1,336, ranked by callers