Functions — github.com/abetlen/llama-cpp-python

hub / github.com/abetlen/llama-cpp-python / functions

Functions1,336 in github.com/abetlen/llama-cpp-python

⨍ Functions 1,336◇ Types & classes 256↳ Endpoints 95

↓ 4 callersMethoddecode

(self, tokens: List[int])

llama_cpp/llama_tokenizer.py:69

↓ 4 callersMethoddelete_free_sequence

(self, seq_id: int)

examples/server/server.py:14949

↓ 4 callersMethodencode

( self, text: str, add_bos: bool = True, special: bool = True )

llama_cpp/llama_tokenizer.py:62

↓ 4 callersMethodencode_sse_payload

(payload: BaseModel | Dict[str, Any])

examples/server/server.py:7855

↓ 4 callersMethodenqueue

(self, command: Callable[[], None])

examples/server/server.py:15484

↓ 4 callersFunctiongenerate_type_definition

( param: Dict[str, llama_types.JsonType], indent_level: int, shared_defs )

llama_cpp/llama_chat_format.py:1491

↓ 4 callersMethodinteract

(self)

examples/low_level_api/low_level_api_chat_cpp.py:699

↓ 4 callersMethodlength

(self, sequence_id: int)

examples/server/server.py:935

↓ 4 callersMethodload

(cls, path: str)

examples/server/server.py:3468

↓ 4 callersMethodlongest_token_prefix

(a: Sequence[int], b: Sequence[int])

llama_cpp/llama.py:2306

↓ 4 callersMethodmatch_prefix

(self, tokens: Sequence[int])

examples/server/server.py:12686

↓ 4 callersMethodmtmd_free

()

llama_cpp/llama_chat_format.py:3316

↓ 4 callersMethodparse_chat_response

( self, response_text: str, *, partial: bool, )

examples/server/server.py:7135

↓ 4 callersMethodrequest_from_prepared

( self, *, payload: CreateCompletionRequest, prompt_text: str, prompt_

examples/server/server.py:15648

↓ 4 callersMethodresolve_model_path

(self)

examples/server/server.py:3457

↓ 4 callersMethodsave_state

(self)

llama_cpp/llama.py:2199

↓ 4 callersMethodsegment_at

(self, pos: int)

examples/server/server.py:4012

↓ 4 callersMethodsubmit_request

( self, request: CompletionRequest, )

examples/server/server.py:15567

↓ 4 callersMethodtoken_to_str

(self, token_id: int)

examples/low_level_api/low_level_api_chat_cpp.py:638

↓ 4 callersMethodtruncate

(self, sequence_id: int, keep_len: int)

examples/server/server.py:938

↓ 4 callersFunctionwatch_http_disconnect

( http_request: Request, cancel: Callable[[], None], )

examples/server/server.py:15748

↓ 3 callersMethod_add_response_stream_item

( self, state: "OpenAIFormatter.ResponsesStream", item: Dict[str, Any], *,

examples/server/server.py:9188

↓ 3 callersMethod_append_parsed_text

(parsed: Dict[str, Any], key: str, text: str)

examples/server/server.py:5400

↓ 3 callersMethod_chat_template_text

(self)

examples/server/server.py:7912

↓ 3 callersMethod_clone_response_input_items

(input_items: Any)

examples/server/server.py:8283

↓ 3 callersMethod_coerce_tool_argument

( self, raw_value: str, schema: Dict[str, Any], *, tool_name: str,

examples/server/server.py:6997

↓ 3 callersMethod_consume_optional_literal_prefix

( cls, pattern: str, )

examples/server/server.py:4584

↓ 3 callersMethod_consume_until_any_literal

( cls, text: str, literals: Sequence[str], )

examples/server/server.py:4872

↓ 3 callersMethod_convert_completion_logprobs_to_chat_choice

( logprobs: Optional[CompletionLogprobs], )

examples/server/server.py:9678

↓ 3 callersMethod_convert_completion_logprobs_to_chat_chunk

( logprobs: Optional[CompletionLogprobs], )

examples/server/server.py:9715

↓ 3 callersMethod_format_literal

(self, literal)

llama_cpp/llama_grammar.py:392

↓ 3 callersMethod_literal_content_for_template

( text: str, media_marker: Optional[str], )

examples/server/server.py:3583

↓ 3 callersMethod_literal_suffix_prefix_length

(text: str, literal: str)

examples/server/server.py:4728

↓ 3 callersMethod_max_bytes_for_media

(self, kind: Literal["image", "audio", "video"])

examples/server/server.py:10627

↓ 3 callersMethod_message_deltas

( self, previous_message: Dict[str, Any], message: Dict[str, Any], )

examples/server/server.py:7418

↓ 3 callersMethod_new_tool_call_state

(self, item_plan: Dict[str, Any])

examples/server/server.py:5479

↓ 3 callersMethod_parameter_schema_for_tool

( self, tool_name: str, parameter_name: str )

examples/server/server.py:5224

↓ 3 callersMethod_parse_response_value

( self, text: Any, schema: Dict[str, Any], *, partial: bool, )

examples/server/server.py:6734

↓ 3 callersMethod_remove_entry

(self, entry: "SequenceDiskCache.Entry")

examples/server/server.py:12510

↓ 3 callersMethod_response_parser

( self, *, tools: Optional[List[ChatTemplateTool]] = None, completion_id: str

examples/server/server.py:8452

↓ 3 callersMethod_tool_content_type

(self, tool_name: str)

examples/server/server.py:5241

↓ 3 callersMethod_tools_for_response_parser

( *, functions: Optional[List[ChatTemplateFunctionDefinition]] = None, tools: Optional

examples/server/server.py:7897

↓ 3 callersMethod_truncate_memory

(self, seq_id: int, keep_len: int)

examples/server/server.py:2381

↓ 3 callersMethodadd_dist

(self, seed: int)

llama_cpp/_internals.py:702

↓ 3 callersMethodclear_sequence_cache_match

(request: CompletionRequest)

examples/server/server.py:13166

↓ 3 callersFunctioncollect_completion_result

( formatter: OpenAIFormatter, http_request: Request, stream: CompletionStream,

examples/server/server.py:15770

↓ 3 callersMethodconvert_completion_chunk_to_chat_chunks

( self, chunk: CompletionChunk, started_indices: set[int], tool_name: Optional

examples/server/server.py:9858

↓ 3 callersMethodcreate_chat_completion

Generate a chat completion from a list of messages. Args: messages: A list of messages to generate a response for. fu

llama_cpp/llama.py:1997

↓ 3 callersFunctionctypes_function_for_shared_library

Decorator for defining ctypes functions with type hints

llama_cpp/_ctypes_extensions.py:140

↓ 3 callersMethodexit

(self)

examples/low_level_api/low_level_api_chat_cpp.py:634

↓ 3 callersMethodfinalize_cancelled

(self)

examples/server/server.py:15449

↓ 3 callersMethodfinish_completion

(self, completion: Completion, finish_reason: str)

examples/server/server.py:14832

↓ 3 callersMethodfrom_tokens

( cls, text: str, tokens: List[int], *, generation_prompt: str = "",

examples/server/server.py:3925

↓ 3 callersMethodhas_text_token_at

(self, pos: int)

examples/server/server.py:4018

↓ 3 callersMethodinput

(self, prompt: str)

examples/low_level_api/low_level_api_chat_cpp.py:653

↓ 3 callersMethodis_reusable_boundary

(self, pos: int)

examples/server/server.py:3976

↓ 3 callersMethodkv_cache_seq_rm

(self, seq_id: int, p0: int, p1: int)

llama_cpp/_internals.py:298

↓ 3 callersFunctionload_shared_library

Platform independent shared library loader

llama_cpp/_ctypes_extensions.py:26

↓ 3 callersMethodload_state

(self, state: LlamaState)

llama_cpp/llama.py:2229

↓ 3 callersMethodlogits_to_logprobs

( logits: Union[npt.NDArray[np.single], List], axis: int = -1 )

llama_cpp/llama.py:2288

↓ 3 callersMethodlongest_prefix

( self, tokens: Sequence[int], preferred_sequences: Optional[Any] = None, *,

examples/server/server.py:1001

↓ 3 callersMethodmaybe_save_sequence_cache

(self, request: CompletionRequest)

examples/server/server.py:13314

↓ 3 callersMethodmetadata

(self)

llama_cpp/_internals.py:210

↓ 3 callersMethodn_ctx_train

(self)

llama_cpp/_internals.py:97

↓ 3 callersMethodnormalized_prompt

(self)

examples/server/server.py:2548

↓ 3 callersFunctionopt_repetitions

- n=4, no sep: '(a (a (a (a)?)?)?)?' - n=4, sep=',', prefix: '("," a ("," a ("," a ("," a)?)?)?)?' - n=4, sep=

llama_cpp/llama_grammar.py:273

↓ 3 callersMethodoutput_index_to_logits_index

( output_index: Optional[int], output_count: int, )

examples/server/server.py:14602

↓ 3 callersFunctionprepare_request_resources

( body: CreateCompletionRequest | CreateChatCompletionRequest, llama_proxy: LlamaProxy, body_model

llama_cpp/server/app.py:158

↓ 3 callersMethodreclaim_order

(self, best_free: Optional[int])

examples/server/server.py:12620

↓ 3 callersMethodrecord_draft_acceptance_length

(self, accepted_tokens: int)

examples/server/server.py:15146

↓ 3 callersMethodrequest_needs_prompt_logits

(request: CompletionRequest)

examples/server/server.py:13156

↓ 3 callersMethodreuse_len_for_request

(request: CompletionRequest, match_length: int)

examples/server/server.py:12693

↓ 3 callersMethodsample

Sample a token from the model. Args: top_k: The top-k sampling parameter. top_p: The top-p sampling parameter.

llama_cpp/llama.py:785

↓ 3 callersMethodsample_completion_token

(self, completion: Completion, output_index: int)

examples/server/server.py:14358

↓ 3 callersFunctionsend_error

(message: str)

examples/server/server.py:16213

↓ 3 callersMethodset_cache

Set the cache. Args: cache: The cache to set.

llama_cpp/llama.py:633

↓ 3 callersMethodset_seed

Set the random seed. Args: seed: The random seed.

llama_cpp/llama.py:641

↓ 3 callersMethodstart_completions

( self, request: CompletionRequest, prompt_output_index: Optional[int], prompt

examples/server/server.py:14617

↓ 3 callersMethodstart_response_stream

( self, state: "OpenAIFormatter.ResponsesStream", )

examples/server/server.py:9161

↓ 3 callersMethodto_template_function

(self)

examples/server/server.py:2781

↓ 3 callersMethodtoken_bytes_with_prev

(self, prev_tokens: Sequence[int], token: int)

examples/server/server.py:12065

↓ 3 callersMethodtoken_get_text

(self, token: int)

llama_cpp/_internals.py:122

↓ 3 callersMethodtry_set_sequence_cache_match

( self, request: CompletionRequest, resident_reuse_len: int, required_sequence

examples/server/server.py:12643

↓ 2 callersMethod_add_entry

( self, *, path: Path, tokens: Tuple[int, ...], has_prompt_logits: boo

examples/server/server.py:12483

↓ 2 callersMethod_advance_stream_state

(self, text: str)

examples/server/server.py:6380

↓ 2 callersMethod_advance_tool_call_state

( self, item_state: Dict[str, Any], text: str, item_plan: Dict[str, Any],

examples/server/server.py:6003

↓ 2 callersMethod_allocate_pending_tokens

( self, sources: Sequence[Union[CompletionRequest, Completion]], capacity: int, )

examples/server/server.py:13810

↓ 2 callersMethod_append_visible_text

(self, key: str, text: str)

examples/server/server.py:5409

↓ 2 callersMethod_apply_lora_adapters

(self, ctx: Any, context_name: str)

examples/server/server.py:11791

↓ 2 callersFunction_assert_prompt_cache_reset_handles_history_edit

( model_path, *, is_recurrent: bool, is_hybrid: bool, )

tests/test_llama.py:292

↓ 2 callersMethod_batch_embeddings

(self)

examples/server/server.py:1411

↓ 2 callersMethod_build_key

( *, model_fingerprint: str, mmproj_fingerprint: str, kind: Literal["image", "

examples/server/server.py:10439

↓ 2 callersMethod_build_object_rule

( self, properties: List[Tuple[str, Any]], required: Set[str], name: str,

llama_cpp/llama_grammar.py:856

↓ 2 callersMethod_build_object_rule

( self, properties: List[Tuple[str, Any]], required: set[str], name: str,

examples/server/server.py:678

↓ 2 callersMethod_build_pending_batch_item

( self, source: Union[CompletionRequest, Completion], token_count: int, output

examples/server/server.py:13860

↓ 2 callersMethod_chat_tool_name_and_grammar

( self, *, tools: Optional[List[ChatTemplateTool]], function_call: Optional[Un

examples/server/server.py:8486

↓ 2 callersMethod_common_prefix_len

( label: Sequence[int], tokens: Sequence[int], offset: int, )

examples/server/server.py:822

↓ 2 callersMethod_compile_capture_pattern

( cls, pattern: str, )

examples/server/server.py:4817

↓ 2 callersMethod_compile_iterator_block_pattern

( cls, pattern: str, )

examples/server/server.py:4774

↓ 2 callersMethod_compile_tool_call_item_plan

( cls, item_schema: Dict[str, Any], )

examples/server/server.py:4907

← previous next →101–200 of 1,336, ranked by callers