[Misc] Separate out utils.counter and move utils.Device to engine (#27588)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
@@ -31,6 +31,7 @@ from vllm.config.model import (
|
||||
TokenizerMode,
|
||||
)
|
||||
from vllm.engine.arg_utils import EngineArgs
|
||||
from vllm.engine.protocol import Device
|
||||
from vllm.entrypoints.chat_utils import (
|
||||
ChatCompletionMessageParam,
|
||||
ChatTemplateContentFormatOption,
|
||||
@@ -75,8 +76,8 @@ from vllm.transformers_utils.tokenizer import (
|
||||
get_cached_tokenizer,
|
||||
)
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
from vllm.utils import Counter, Device
|
||||
from vllm.utils.collection_utils import as_iter, is_list_of
|
||||
from vllm.utils.counter import Counter
|
||||
from vllm.v1.engine import EngineCoreRequest
|
||||
from vllm.v1.engine.llm_engine import LLMEngine
|
||||
from vllm.v1.sample.logits_processor import LogitsProcessor
|
||||
@@ -1490,8 +1491,8 @@ class LLM:
|
||||
def stop_profile(self) -> None:
|
||||
self.llm_engine.stop_profile()
|
||||
|
||||
def reset_prefix_cache(self, device: Device | None = None) -> bool:
|
||||
return self.llm_engine.reset_prefix_cache(device)
|
||||
def reset_prefix_cache(self, device: Device | None = None) -> None:
|
||||
self.llm_engine.reset_prefix_cache(device)
|
||||
|
||||
def sleep(self, level: int = 1):
|
||||
"""
|
||||
|
||||
@@ -40,7 +40,7 @@ from typing_extensions import assert_never
|
||||
import vllm.envs as envs
|
||||
from vllm.config import VllmConfig
|
||||
from vllm.engine.arg_utils import AsyncEngineArgs
|
||||
from vllm.engine.protocol import EngineClient
|
||||
from vllm.engine.protocol import Device, EngineClient
|
||||
from vllm.entrypoints.launcher import serve_http
|
||||
from vllm.entrypoints.logger import RequestLogger
|
||||
from vllm.entrypoints.openai.cli_args import make_arg_parser, validate_parsed_serve_args
|
||||
@@ -108,7 +108,6 @@ from vllm.entrypoints.utils import (
|
||||
from vllm.logger import init_logger
|
||||
from vllm.reasoning import ReasoningParserManager
|
||||
from vllm.usage.usage_lib import UsageContext
|
||||
from vllm.utils import Device
|
||||
from vllm.utils.argparse_utils import FlexibleArgumentParser
|
||||
from vllm.utils.network_utils import is_valid_ipv6_address
|
||||
from vllm.utils.system_utils import decorate_logs, set_ulimit
|
||||
|
||||
@@ -19,7 +19,7 @@ from vllm.entrypoints.openai.protocol import (
|
||||
from vllm.logger import init_logger
|
||||
from vllm.lora.request import LoRARequest
|
||||
from vllm.lora.resolver import LoRAResolver, LoRAResolverRegistry
|
||||
from vllm.utils import AtomicCounter
|
||||
from vllm.utils.counter import AtomicCounter
|
||||
|
||||
logger = init_logger(__name__)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user