owen/worker-vllm
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Update utils.py

Browse Source
This commit is contained in:
velaraptor-runpod
2026-02-12 15:28:31 -06:00
parent 340bc0b3c6
commit 7ec10b98cd
1 changed files with 4 additions and 4 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/utils.py
+4 -4
View File
@@ -6,7 +6,7 @@ from time import time
try: try:
from vllm.utils import random_uuid from vllm.utils import random_uuid
from vllm.entrypoints.openai.engine.protocol import ErrorResponse, RequestResponseMetadata from vllm.entrypoints.openai.engine.protocol import ErrorResponse, ErrorInfo, RequestResponseMetadata
from vllm import SamplingParams from vllm import SamplingParams
except ImportError: except ImportError:
logging.warning("Error importing vllm, skipping related imports. This is ONLY expected when baking model into docker image from a machine without GPUs") logging.warning("Error importing vllm, skipping related imports. This is ONLY expected when baking model into docker image from a machine without GPUs")
@@ -87,9 +87,9 @@ class BatchSize:
self.current_batch_size = min(self.current_batch_size*self.batch_size_growth_factor, self.max_batch_size) self.current_batch_size = min(self.current_batch_size*self.batch_size_growth_factor, self.max_batch_size)
def create_error_response(message: str, err_type: str = "BadRequestError", status_code: HTTPStatus = HTTPStatus.BAD_REQUEST) -> ErrorResponse: def create_error_response(message: str, err_type: str = "BadRequestError", status_code: HTTPStatus = HTTPStatus.BAD_REQUEST) -> ErrorResponse:
return ErrorResponse(message=message, return ErrorResponse(error=ErrorInfo(message=message,
type=err_type, type=err_type,
code=status_code.value) code=status_code.value))
def get_int_bool_env(env_var: str, default: bool) -> bool: def get_int_bool_env(env_var: str, default: bool) -> bool:
return int(os.getenv(env_var, int(default))) == 1 return int(os.getenv(env_var, int(default))) == 1