[Core][Bugfix][Perf] Introduce MQLLMEngine to avoid asyncio OH (#8157)
Co-authored-by: Nick Hill <nickhill@us.ibm.com> Co-authored-by: rshaw@neuralmagic.com <rshaw@neuralmagic.com> Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com> Co-authored-by: Simon Mo <simon.mo@hey.com>
This commit is contained in:
co-authored by
Nick Hill
rshaw@neuralmagic.com <rshaw@neuralmagic.com>
Robert Shaw
Simon Mo
parent
9d104b5beb
commit
7c7714d856
@@ -14,8 +14,8 @@ from vllm.transformers_utils.tokenizer import AnyTokenizer
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class AsyncEngineClient(Protocol):
|
||||
"""Protocol class for Clients to AsyncLLMEngine"""
|
||||
class EngineClient(Protocol):
|
||||
"""Protocol class for Clients to Engine"""
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
@@ -30,8 +30,8 @@ class AsyncEngineClient(Protocol):
|
||||
...
|
||||
|
||||
@property
|
||||
def limit_concurrency(self) -> Optional[int]:
|
||||
"""Maximum number of concurrently running requests."""
|
||||
def dead_error(self) -> BaseException:
|
||||
...
|
||||
|
||||
def generate(
|
||||
self,
|
||||
|
||||
Reference in New Issue
Block a user