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

↓ 1 callersMethod_ordered_pending_sequences

( self, prompt_requests: Sequence[CompletionRequest], completions: Sequence[Completion

examples/server/server.py:13727

↓ 1 callersMethod_parse_pooling_type

(value: str)

examples/server/server.py:11869

↓ 1 callersMethod_partial_regex_key_value_item

( pattern: str, text: str, *, min_start: int, )

examples/server/server.py:6673

↓ 1 callersMethod_passes_p_min

(self, output_index: int)

examples/server/server.py:1352

↓ 1 callersMethod_pattern_has_glob

(pattern: str)

examples/server/server.py:3181

↓ 1 callersMethod_pick_sequence

(candidates: set[int], preferred_sequences: Optional[Any])

examples/server/server.py:803

↓ 1 callersMethod_positions_for_chunk

(self, chunk: Any, start_pos: int)

examples/server/server.py:10934

↓ 1 callersMethod_postprocess_template_text

( self, text: str, image_urls: List[str], media_marker: str, )

llama_cpp/llama_chat_format.py:3392

↓ 1 callersMethod_process_rows

( self, batch: Any, h_tgt_rows: np.ndarray, start: int, end: int,

examples/server/server.py:1603

↓ 1 callersMethod_raw_string_tool_arguments

(self, tool_name: str, value: str)

examples/server/server.py:5250

↓ 1 callersMethod_read_entry_header

(self, path: Path)

examples/server/server.py:12413

↓ 1 callersMethod_read_entry_payload

( self, entry: "SequenceDiskCache.Entry", )

examples/server/server.py:12427

↓ 1 callersMethod_regex_capture_end_literals

(cls, pattern: str)

examples/server/server.py:4683

↓ 1 callersMethod_regex_leading_capture

( cls, *, field_name: str, field_regex: str, content_regex: Optional[s

examples/server/server.py:4687

↓ 1 callersMethod_regex_lookahead_literal_specs

(cls, pattern: str)

examples/server/server.py:4633

↓ 1 callersMethod_renumber_output_indices

( items: Sequence["CompletionScheduler.BatchItem"], )

examples/server/server.py:13616

↓ 1 callersMethod_reserved_names

(cls)

examples/server/server.py:284

↓ 1 callersMethod_resolve_ref

(self, ref)

llama_cpp/llama_grammar.py:685

↓ 1 callersMethod_resolve_ref

(self, ref: str)

examples/server/server.py:514

↓ 1 callersMethod_response_chat_content_from_content

( content: Any, )

examples/server/server.py:7969

↓ 1 callersMethod_response_custom_tool_call_input_message

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

examples/server/server.py:8116

↓ 1 callersMethod_response_format_type

(response_format: Optional[ChatTemplateResponseFormat])

examples/server/server.py:8393

↓ 1 callersMethod_response_from_chat_message

( self, *, body: CreateResponseRequest, response_id: str, created_at:

examples/server/server.py:9056

↓ 1 callersMethod_response_function_call_input_message

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

examples/server/server.py:8098

↓ 1 callersMethod_response_item_status

( finish_reason: Optional[str], )

examples/server/server.py:9181

↓ 1 callersMethod_response_logprobs_from_chat_logprobs

( logprobs: Optional[Dict[str, Any]], )

examples/server/server.py:8698

↓ 1 callersMethod_response_logprobs_from_completion

( self, logprobs: Optional[CompletionLogprobs], )

examples/server/server.py:8735

↓ 1 callersMethod_response_output_items_from_message

( self, *, response_id: str, message: Dict[str, Any], logprobs: Option

examples/server/server.py:8885

↓ 1 callersMethod_response_output_text_from_message

(message: Dict[str, Any])

examples/server/server.py:8689

↓ 1 callersMethod_response_phase_from_message

(message: Dict[str, Any])

examples/server/server.py:8663

↓ 1 callersMethod_response_reasoning_input_message

( self, *, text: str, )

examples/server/server.py:8043

↓ 1 callersMethod_response_reasoning_text

(item: Dict[str, Any])

examples/server/server.py:8034

↓ 1 callersMethod_response_reasoning_text_from_message

(message: Dict[str, Any])

examples/server/server.py:8675

↓ 1 callersMethod_responses_tool_choice_to_chat_tool_choice

( tool_choice: Optional[ResponsesToolChoice], )

examples/server/server.py:8381

↓ 1 callersMethod_responses_tools_to_chat_tools

( self, tools: Optional[List[ResponsesToolDefinition]], )

examples/server/server.py:8352

↓ 1 callersMethod_safe_open

(path: Path)

examples/server/server.py:10412

↓ 1 callersMethod_save_file

( tensors: Dict[str, np.ndarray], path: Path, metadata: Dict[str, str], )

examples/server/server.py:10423

↓ 1 callersMethod_save_file

( tensors: Dict[str, np.ndarray], path: Path, metadata: Dict[str, str], )

examples/server/server.py:12399

↓ 1 callersMethod_save_media_chunk

(self, media_chunk: "MTMDProcessor.MediaChunk")

examples/server/server.py:10867

↓ 1 callersMethod_serialize_partial_json_prefix

(cls, value: Any)

examples/server/server.py:7255

↓ 1 callersMethod_serialize_partial_json_state

(cls, value: Any)

examples/server/server.py:7314

↓ 1 callersMethod_single_string_tool_argument_name

(self, tool_name: str)

examples/server/server.py:5282

↓ 1 callersMethod_split_mixed_mtp_batch

( self, items: List["CompletionScheduler.BatchItem"], )

examples/server/server.py:13597

↓ 1 callersMethod_split_regex_alternatives

(pattern: str)

examples/server/server.py:4599

↓ 1 callersMethod_start_sampled_draft_states

( self, updates: Sequence["MTPDraftProvider.SampledBatchUpdate"], sampled_outputs: Seq

examples/server/server.py:2186

↓ 1 callersFunction_stream_response_to_function_stream

( chunks: Iterator[llama_types.CreateCompletionStreamResponse], )

llama_cpp/llama_chat_format.py:478

↓ 1 callersMethod_stream_state_complete

(self)

examples/server/server.py:7562

↓ 1 callersMethod_subfolder_for_repo_file

(repo_file: str)

examples/server/server.py:3185

↓ 1 callersMethod_tool_call_delta

( self, *, tool_call: Dict[str, Any], tool_call_index: int, partial: b

examples/server/server.py:6352

↓ 1 callersMethod_tool_schema_map

( tools: Optional[List[ChatTemplateTool]], )

examples/server/server.py:5190

↓ 1 callersMethod_trim_partial_gemma_quote_marker

(value: str)

examples/server/server.py:5386

↓ 1 callersMethod_trim_partial_tool_call_prefix

( self, *, response_text: str, parsed: Dict[str, Any], )

examples/server/server.py:6708

↓ 1 callersMethod_try_decode_batch_for_mtp_head

(self, head: int)

examples/server/server.py:1465

↓ 1 callersMethod_update_tool_stream_item

( self, item: Dict[str, Any], *, call_id: Optional[str], name_delta: O

examples/server/server.py:9308

↓ 1 callersMethod_urlopen_without_redirects

( request: urllib.request.Request, *, timeout: float, )

examples/server/server.py:10670

↓ 1 callersMethod_uses_reasoning_content

(self)

examples/server/server.py:7921

↓ 1 callersMethod_validate_remote_media_url

(self, media_url: str)

examples/server/server.py:10656

↓ 1 callersMethod_video_temp_suffix

(media: MediaInput)

examples/server/server.py:10770

↓ 1 callersMethod_visit_pattern

Transforms a regular expression pattern into a GBNF rule. Input: https://json-schema.org/understanding-json-schema/reference/regular

llama_cpp/llama_grammar.py:500

↓ 1 callersMethod_visit_pattern

(self, pattern: str, name: str)

examples/server/server.py:364

↓ 1 callersMethod_write_entry

( self, path: Path, tensors: Dict[str, np.ndarray], )

examples/server/server.py:12452

↓ 1 callersMethodactive_draft_batch_size_allowed

(self, draft_batch_size: int)

examples/server/server.py:13514

↓ 1 callersFunctionadd_args_from_model

Add arguments from a pydantic model to an argparse parser.

llama_cpp/server/cli.py:82

↓ 1 callersMethodadd_batch_embeddings

( self, *, seq_id: int, embeddings: np.ndarray, positions: np.ndarray,

examples/server/server.py:12107

↓ 1 callersMethodadd_bos_token

(self)

llama_cpp/_internals.py:160

↓ 1 callersMethodadd_custom

( self, apply_func: Callable[[llama_cpp.llama_token_data_array], None] )

llama_cpp/_internals.py:843

↓ 1 callersMethodadd_eos_token

(self)

llama_cpp/_internals.py:163

↓ 1 callersMethodadd_grammar

(self, model: LlamaModel, grammar: LlamaGrammar)

llama_cpp/_internals.py:753

↓ 1 callersMethodadd_greedy

(self)

llama_cpp/_internals.py:698

↓ 1 callersMethodadd_min_p

(self, p: float, min_keep: int = 1)

llama_cpp/_internals.py:721

↓ 1 callersMethodadd_mirostat

(self, n_vocab: int, seed: int, tau: float, eta: float, m: int)

llama_cpp/_internals.py:745

↓ 1 callersMethodadd_mirostat_v2

(self, seed: int, tau: float, eta: float)

llama_cpp/_internals.py:749

↓ 1 callersMethodadd_penalties

( self, penalty_last_n: int, penalty_repeat: float, penalty_freq: float,

llama_cpp/_internals.py:785

↓ 1 callersMethodadd_sequence

(self, batch: Sequence[int], seq_id: int, logits_all: bool)

llama_cpp/_internals.py:516

↓ 1 callersMethodadd_typical

(self, p: float, min_keep: int = 1)

llama_cpp/_internals.py:725

↓ 1 callersMethodadmit_request

(self, request: CompletionRequest)

examples/server/server.py:12672

↓ 1 callersMethodadmit_request

(self, request: CompletionRequest)

examples/server/server.py:13532

↓ 1 callersMethodadmit_waiting

(self)

examples/server/server.py:13518

↓ 1 callersMethodaggregate_completion_results

( self, results: Sequence[OpenAICompletion], )

examples/server/server.py:9649

↓ 1 callersMethodapply_deferred_draft_rollbacks

( self, items: Sequence["CompletionScheduler.BatchItem"], )

examples/server/server.py:14313

↓ 1 callersMethodapply_func

(token_data_array: llama_cpp.llama_token_data_array_p)

llama_cpp/llama.py:719

↓ 1 callersMethodbatch_needs_draft_processing

( self, batch_items: Sequence["CompletionScheduler.BatchItem"], )

examples/server/server.py:13472

↓ 1 callersMethodbuild_batch

(self)

examples/server/server.py:13537

↓ 1 callersMethodbuild_completion_response

( self, request: CompletionRequest, completions: Sequence[Completion], )

examples/server/server.py:10235

↓ 1 callersMethodbuild_memory_policy

(self)

examples/server/server.py:13117

↓ 1 callersMethodbuild_model_params

( *, n_gpu_layers: Optional[int], split_mode: Optional[int], main_gpu: Optiona

examples/server/server.py:11582

↓ 1 callersMethodbuild_prompt_plan

( self, *, messages: List[ChatCompletionRequestMessage], functions: Optional[L

examples/server/server.py:10959

↓ 1 callersMethodbuild_prompt_tokens

(self, prompt: str, suffix: Optional[str])

examples/server/server.py:11960

↓ 1 callersMethodcall_on_idle_scheduler

(self, callback: Callable[[], Any])

examples/server/server.py:15510

↓ 1 callersMethodcall_on_scheduler

(self, callback: Callable[[], Any])

examples/server/server.py:15491

↓ 1 callersMethodcan_admit

(self, request: CompletionRequest)

examples/server/server.py:12668

↓ 1 callersMethodcan_admit

(self, request: CompletionRequest)

examples/server/server.py:13529

↓ 1 callersMethodcan_lookup_sequence_cache

(self, request: CompletionRequest)

examples/server/server.py:13170

↓ 1 callersFunctioncancel_all_requests

()

examples/server/server.py:15803

↓ 1 callersMethodcapture_prompt_logprobs

( self, *, model: Model, formatter: OpenAIFormatter, output_indices: S

examples/server/server.py:4261

↓ 1 callersFunctioncheck_magic_and_version

(filename)

docker/open_llama/hug_model.py:16

↓ 1 callersMethodclose

(self)

llama_cpp/_internals.py:280

↓ 1 callersMethodclose

(self)

llama_cpp/_internals.py:493

↓ 1 callersMethodclose

(self)

llama_cpp/_internals.py:692

↓ 1 callersFunctioncollect_completion_results

( formatter: OpenAIFormatter, http_request: Request, submissions: Sequence[

examples/server/server.py:15790

← previous next →401–500 of 1,336, ranked by callers