biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[V1] Refactor get_executor_cls (#11754)

Browse Source
This commit is contained in:
Rui Qiao
2025-01-05 23:59:16 -08:00
committed by GitHub
parent f8fcca100b
commit 022c5c6944
5 changed files with 26 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/v1/engine/test_engine_core.py
View File

@@ -8,8 +8,8 @@ from vllm import SamplingParams
from vllm.engine.arg_utils import EngineArgs
from vllm.platforms import current_platform
from vllm.v1.engine import EngineCoreRequest
from vllm.v1.engine.async_llm import AsyncLLM
from vllm.v1.engine.core import EngineCore
from vllm.v1.executor.abstract import Executor
if not current_platform.is_cuda():
pytest.skip(reason="V1 currently only supported on CUDA.",
@@ -43,7 +43,7 @@ def test_engine_core(monkeypatch):
"""Setup the EngineCore."""
engine_args = EngineArgs(model=MODEL_NAME)
vllm_config = engine_args.create_engine_config()
executor_class = AsyncLLM._get_executor_cls(vllm_config)
executor_class = Executor.get_class(vllm_config)
engine_core = EngineCore(vllm_config=vllm_config,
executor_class=executor_class)
@@ -149,7 +149,7 @@ def test_engine_core_advanced_sampling(monkeypatch):
"""Setup the EngineCore."""
engine_args = EngineArgs(model=MODEL_NAME)
vllm_config = engine_args.create_engine_config()
executor_class = AsyncLLM._get_executor_cls(vllm_config)
executor_class = Executor.get_class(vllm_config)
engine_core = EngineCore(vllm_config=vllm_config,
executor_class=executor_class)

6
tests/v1/engine/test_engine_core_client.py
View File

@@ -11,8 +11,8 @@ from vllm.engine.arg_utils import EngineArgs
from vllm.platforms import current_platform
from vllm.usage.usage_lib import UsageContext
from vllm.v1.engine import EngineCoreRequest
from vllm.v1.engine.async_llm import AsyncLLM
from vllm.v1.engine.core_client import EngineCoreClient
from vllm.v1.executor.abstract import Executor
if not current_platform.is_cuda():
pytest.skip(reason="V1 currently only supported on CUDA.",
@@ -84,7 +84,7 @@ def test_engine_core_client(monkeypatch, multiprocessing_mode: bool):
engine_args = EngineArgs(model=MODEL_NAME, compilation_config=3)
vllm_config = engine_args.create_engine_config(
UsageContext.UNKNOWN_CONTEXT)
executor_class = AsyncLLM._get_executor_cls(vllm_config)
executor_class = Executor.get_class(vllm_config)
client = EngineCoreClient.make_client(
multiprocess_mode=multiprocessing_mode,
asyncio_mode=False,
@@ -152,7 +152,7 @@ async def test_engine_core_client_asyncio(monkeypatch):
engine_args = EngineArgs(model=MODEL_NAME)
vllm_config = engine_args.create_engine_config(
usage_context=UsageContext.UNKNOWN_CONTEXT)
executor_class = AsyncLLM._get_executor_cls(vllm_config)
executor_class = Executor.get_class(vllm_config)
client = EngineCoreClient.make_client(
multiprocess_mode=True,
asyncio_mode=True,