[Misc] Collect model support info in a single process per model (#9233)
This commit is contained in:
@@ -183,6 +183,8 @@ class EngineArgs:
|
||||
def __post_init__(self):
|
||||
if self.tokenizer is None:
|
||||
self.tokenizer = self.model
|
||||
|
||||
# Setup plugins
|
||||
from vllm.plugins import load_general_plugins
|
||||
load_general_plugins()
|
||||
|
||||
|
||||
@@ -130,6 +130,9 @@ class MQLLMEngine:
|
||||
def from_engine_args(cls, engine_args: AsyncEngineArgs,
|
||||
usage_context: UsageContext, ipc_path: str):
|
||||
"""Creates an MQLLMEngine from the engine arguments."""
|
||||
# Setup plugins for each process
|
||||
from vllm.plugins import load_general_plugins
|
||||
load_general_plugins()
|
||||
|
||||
engine_config = engine_args.create_engine_config()
|
||||
|
||||
|
||||
Reference in New Issue
Block a user