[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:
Alexander Matveev
2024-09-18 13:56:58 +00:00
committed by GitHub
co-authored by Nick Hill rshaw@neuralmagic.com <rshaw@neuralmagic.com> Robert Shaw Simon Mo
parent 9d104b5beb
commit 7c7714d856
36 changed files with 1464 additions and 1169 deletions
+4 -4
View File
@@ -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,