Functions — github.com/Lightning-AI/LitServe

CodeHub MCPcopy Create free account

hub / github.com/Lightning-AI/LitServe / functions

Functions984 in github.com/Lightning-AI/LitServe

⨍ Functions 984◇ Types & classes 226↳ Endpoints 30

↓ 1 callersMethodpredict

src/litserve/test_examples/openai_spec_example.py:24

↓ 1 callersMethodpredict

(self, inputs, context)

src/litserve/test_examples/openai_spec_example.py:63

↓ 1 callersMethodpredict

src/litserve/test_examples/openai_spec_example.py:108

↓ 1 callersMethodpredict

src/litserve/test_examples/openai_spec_example.py:122

↓ 1 callersMethodpredict

src/litserve/test_examples/openai_spec_example.py:137

↓ 1 callersMethodpredict

tests/parity_fastapi/fastapi-server.py:35

↓ 1 callersMethodpredict

tests/unit/test_loops.py:105

↓ 1 callersMethodpredict

tests/unit/test_litapi.py:56

↓ 1 callersMethodpredict

tests/unit/test_litapi.py:84

↓ 1 callersMethodpredict

tests/unit/test_auth.py:65

↓ 1 callersMethodpredict

tests/unit/test_logger.py:78

↓ 1 callersMethodpredict

tests/unit/test_batch.py:83

↓ 1 callersMethodpredict

tests/e2e/default_batched_streaming.py:26

↓ 1 callersMethodprefill

Fill available capacity with pending and new requests.

src/litserve/loops/continuous_batching_loop.py:132

↓ 1 callersMethodprocess

Process a log entry from the log queue. This method should be implemented to define the specific logic for processing log entries.

src/litserve/loggers.py:45

↓ 1 callersMethodprocess_image

(self, image_data)

tests/parity_fastapi/fastapi-server.py:29

↓ 1 callersMethodregister_endpoints

src/litserve/server.py:1027

↓ 1 callersFunctionresponse_queue_to_buffer

( transport: MessageTransport, response_buffer: dict[str, ResponseBufferItem], consumer_id: int,

src/litserve/server.py:133

↓ 1 callersFunctionrun_fastapi_benchmark

tests/parity_fastapi/main.py:64

↓ 1 callersFunctionrun_litserve_benchmark

tests/parity_fastapi/main.py:71

↓ 1 callersFunctionrun_script_with_timeout

(file, timeout, extra_time, killall)

tests/unit/test_readme.py:50

↓ 1 callersMethodschedule_task

( self, lit_api: LitAPI, lit_spec: Optional[LitSpec], request_queue: Queue,

src/litserve/loops/base.py:220

↓ 1 callersMethodsend

(self, item, consumer_id, block=False, timeout=None)

tests/unit/test_loops.py:192

↓ 1 callersFunctionset_log_level

Allow users to set the global logging level for the library.

src/litserve/utils.py:195

↓ 1 callersMethodset_logger_queue

Set the queue for logging events.

src/litserve/api.py:382

↓ 1 callersMethodset_request_timeout

(self, timeout: float)

src/litserve/server.py:254

↓ 1 callersFunctionset_trace

Set a tracepoint in the code.

src/litserve/utils.py:240

↓ 1 callersMethodsetup

(self, device: str)

src/litserve/test_examples/openai_spec_example.py:57

↓ 1 callersMethodsetup

src/litserve/test_examples/openai_spec_example.py:105

↓ 1 callersMethodsetup

src/litserve/test_examples/openai_spec_example.py:119

↓ 1 callersMethodsetup

This method is called by the server to connect the spec to the server.

src/litserve/specs/base.py:47

↓ 1 callersMethodsetup

tests/unit/test_loops.py:99

↓ 1 callersMethodsetup

(self, spec: Optional[LitSpec])

tests/unit/test_loops.py:875

↓ 1 callersMethodsetup

tests/unit/test_litapi.py:299

↓ 1 callersMethodsetup

tests/unit/test_schema.py:28

↓ 1 callersMethodsetup

tests/unit/test_batch.py:75

↓ 1 callersFunctionsimple_litapi_cls

tests/conftest.py:109

↓ 1 callersFunctionspeed_test

tests/perf_test/stream/stream_speed/benchmark.py:40

↓ 1 callersMethodstep

( self, prev_outputs: Optional[list[Output]], lit_api: LitAPI, lit_spec: Optional[LitSpec] )

src/litserve/loops/continuous_batching_loop.py:210

↓ 1 callersMethodstreamable_http_app

src/litserve/mcp.py:464

↓ 1 callersMethodstreaming_completion

(self, request: ChatCompletionRequest, pipe_responses: list)

src/litserve/specs/openai.py:536

↓ 1 callersFunctiontest_worker_monitoring_triggers_shutdown_on_worker_death

Test that server shuts down when a worker dies.

tests/unit/test_failed_workers.py:26

↓ 1 callersMethodunbatch

src/litserve/test_examples/openai_spec_example.py:94

↓ 1 callersMethodunbatch

src/litserve/test_examples/openai_spec_example.py:150

↓ 1 callersMethodverify_worker_status

src/litserve/server.py:1106

(self, scope: Scope, receive: Receive, send: Send)

src/litserve/middlewares.py:37

(self, scope: Scope, receive: Receive, send: Send)

src/litserve/middlewares.py:63

(cls, *args, **kwargs)

src/litserve/utils.py:274

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

src/litserve/loops/base.py:229

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

src/litserve/loops/streaming_loops.py:281

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

src/litserve/loops/streaming_loops.py:397

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

src/litserve/loops/simple_loops.py:293

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

src/litserve/loops/simple_loops.py:420

( self, lit_api: LitAPI, device: str, worker_id: int, request_queue: Q

tests/unit/test_loops.py:673

Method__getattr__

src/litserve/specs/base.py:83

Method__getstate__

Exclude _server from pickling as it contains unpickleable objects.

src/litserve/specs/base.py:34

Args: name: The name of the MCP tool. description: The description of the MCP tool. input_schema: The inp

src/litserve/mcp.py:348

(self, mcp_server: "MCPServer")

src/litserve/mcp.py:418

src/litserve/mcp.py:491

Initialize LitAPI with configuration options.

src/litserve/api.py:139

( self, app: ASGIApp, *, max_size: Optional[int] = None, )

src/litserve/middlewares.py:28

(self, app: ASGIApp, active_counter: multiprocessing.Value)

src/litserve/middlewares.py:59

src/litserve/loggers.py:30

(self, logger_class)

src/litserve/loggers.py:79

(self, lit_server: "LitServer", loggers: Optional[Union[list[Logger], Logger]] = None)

src/litserve/loggers.py:96

(self, accelerator: str = "auto", devices: Union[list[int], int, str] = "auto")

src/litserve/connector.py:23

(self, lit_apis: Union[LitAPI, Iterable[LitAPI]])

src/litserve/server.py:229

(self, lit_api: LitAPI, server: "LitServer")

src/litserve/server.py:281

( self, lit_api: Union[LitAPI, list[LitAPI]], accelerator: Literal["cpu", "cuda", "mps

src/litserve/server.py:659

(self, message: str = _DEFAULT_STOP_LOOP_MESSAGE)

src/litserve/loops/base.py:94

Runs continuous batching loop. This loop handles adding new requests, processing them in batches, and managing the state of active sequences.

src/litserve/loops/continuous_batching_loop.py:57

src/litserve/test_examples/simple_example.py:45

(self, use_process: bool = False)

src/litserve/transport/zmq_queue.py:34

(self, address: str = None)

src/litserve/transport/zmq_queue.py:86

(self, consumer_id: int, address: str)

src/litserve/transport/zmq_queue.py:136

(self, backend_address: str, frontend_address)

src/litserve/transport/zmq_transport.py:10

(self, manager: Manager, queues: list[Queue])

src/litserve/transport/process_transport.py:10

(self, callbacks: Union[Callback, list[Callback]] = None)

src/litserve/callbacks/base.py:65

src/litserve/specs/openai_embedding.py:128

src/litserve/specs/base.py:25

(self, spec: LitSpec)

src/litserve/specs/base.py:80

src/litserve/specs/openai.py:359

tests/conftest.py:387

tests/parity_fastapi/fastapi-server.py:23

(self, num_consumers=1)

tests/unit/test_loops.py:59

(self, num_streamed_outputs)

tests/unit/test_loops.py:187

(self, num_streamed_outputs)

tests/unit/test_loops.py:309

tests/unit/test_litapi.py:288

(self, app: ASGIApp, length: int)

tests/unit/test_middlewares.py:29

(self, arg1, arg2, arg3)

tests/unit/test_simple.py:380

tests/unit/test_lit_server.py:137

(self, json_data=None, form_data=None, content_type="application/json")

tests/unit/test_request_handlers.py:50

(self, lit_api, server)

tests/unit/test_request_handlers.py:65

tests/unit/test_torch.py:25

(self, *args, **kwargs)

tests/unit/test_logger.py:150

(self, name=None, *args, **kwargs)

tests/unit/test_multiple_endpoints.py:10

tests/unit/test_batch.py:39

tests/unit/test_batch.py:198

src/litserve/server.py:262

(mcls, name, bases, namespace, **kwargs)

src/litserve/utils.py:257

← previous next →201–300 of 984, ranked by callers