[Refactor] TokenizerRegistry only uses lazy imports (#30609)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -26,7 +26,7 @@ from vllm.plugins.io_processors import get_io_processor
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.tasks import SupportedTask
|
||||
from vllm.tokenizers import TokenizerLike, init_tokenizer_from_config
|
||||
from vllm.tokenizers import TokenizerLike, cached_tokenizer_from_config
|
||||
from vllm.tracing import init_tracer
|
||||
from vllm.transformers_utils.config import maybe_register_config_serialize_by_value
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
@@ -111,7 +111,7 @@ class AsyncLLM(EngineClient):
|
||||
if self.model_config.skip_tokenizer_init:
|
||||
tokenizer = None
|
||||
else:
|
||||
tokenizer = init_tokenizer_from_config(self.model_config)
|
||||
tokenizer = cached_tokenizer_from_config(self.model_config)
|
||||
|
||||
self.input_processor = InputProcessor(self.vllm_config, tokenizer)
|
||||
self.io_processor = get_io_processor(
|
||||
|
||||
@@ -23,7 +23,7 @@ from vllm.plugins.io_processors import get_io_processor
|
||||
from vllm.pooling_params import PoolingParams
|
||||
from vllm.sampling_params import SamplingParams
|
||||
from vllm.tasks import SupportedTask
|
||||
from vllm.tokenizers import TokenizerLike, init_tokenizer_from_config
|
||||
from vllm.tokenizers import TokenizerLike, cached_tokenizer_from_config
|
||||
from vllm.tracing import init_tracer
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
@@ -86,7 +86,7 @@ class LLMEngine:
|
||||
if self.model_config.skip_tokenizer_init:
|
||||
tokenizer = None
|
||||
else:
|
||||
tokenizer = init_tokenizer_from_config(self.model_config)
|
||||
tokenizer = cached_tokenizer_from_config(self.model_config)
|
||||
|
||||
self.input_processor = InputProcessor(self.vllm_config, tokenizer)
|
||||
self.io_processor = get_io_processor(
|
||||
|
||||
@@ -7,7 +7,7 @@ from typing import TYPE_CHECKING
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.logger import init_logger
|
||||
from vllm.reasoning import ReasoningParserManager
|
||||
from vllm.tokenizers import init_tokenizer_from_config
|
||||
from vllm.tokenizers import cached_tokenizer_from_config
|
||||
from vllm.utils.import_utils import LazyLoader
|
||||
from vllm.v1.structured_output.backend_guidance import GuidanceBackend
|
||||
from vllm.v1.structured_output.backend_types import (
|
||||
@@ -71,7 +71,7 @@ class StructuredOutputManager:
|
||||
# of CPUs.
|
||||
max_workers = max(1, (multiprocessing.cpu_count() + 1) // 2)
|
||||
self.executor = ThreadPoolExecutor(max_workers=max_workers)
|
||||
self.tokenizer = init_tokenizer_from_config(
|
||||
self.tokenizer = cached_tokenizer_from_config(
|
||||
model_config=self.vllm_config.model_config
|
||||
)
|
||||
reasoning_parser = (
|
||||
|
||||
Reference in New Issue
Block a user