[Feature] support pool (#3827)

* support pool

* update pooling

* add pooler_config and check

* update

* support AutoWeightsLoader load weight

* fix

* update

* delete print

* update pre-commit

* fix

* fix xpu

* fix ModelRegistry->model_registry

* fix Copilot review

* fix pooler.py

* delete StepPooler

* fix abstract

* fix default_loader_v1

* fix Pre Commit

* support torch qwen3 dense

* add test and fix torch-qwen

* fix

* fix

* adapter ci:

* fix review

* fix pooling_params.py

* fix

* fix tasks.py 2025

* fix print and logger

* Modefy ModelRegistry and delete AutoWeightsLoader

* fix logger

* fix test_embedding

* fix ci bug

* ernie4_5 model_registry

* fix test

* support Qwen3-Embedding-0.6B tp=1 load

* fix extra code

* fix

* delete fix vocab_size

* delete prepare_params_dict

* fix:
This commit is contained in:
lizexu123
2025-09-22 14:09:09 +08:00
committed by GitHub
parent da74a5f0b3
commit c86945ef49
36 changed files with 2371 additions and 51 deletions

View File

@@ -51,6 +51,7 @@ from fastdeploy.entrypoints.openai.protocol import ErrorInfo, ErrorResponse
from fastdeploy.logger.logger import FastDeployLogger
T = TypeVar("T")
from typing import Callable, Optional
# [N,2] -> every line is [config_name, enable_xxx_name]
# Make sure enable_xxx equal to config.enable_xxx
@@ -852,3 +853,24 @@ api_server_logger = get_logger("api_server", "api_server.log")
console_logger = get_logger("console", "console.log", print_to_console=True)
spec_logger = get_logger("speculate", "speculate.log")
zmq_client_logger = get_logger("zmq_client", "zmq_client.log")
def parse_type(return_type: Callable[[str], T]) -> Callable[[str], T]:
def _parse_type(val: str) -> T:
try:
return return_type(val)
except ValueError as e:
raise argparse.ArgumentTypeError(f"Value {val} cannot be converted to {return_type}.") from e
return _parse_type
def optional_type(return_type: Callable[[str], T]) -> Callable[[str], Optional[T]]:
def _optional_type(val: str) -> Optional[T]:
if val == "" or val == "None":
return None
return parse_type(return_type)(val)
return _optional_type