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

[V1] [4/N] API Server: ZMQ/MP Utilities (#11541)

Browse Source
This commit is contained in:
Robert Shaw
2024-12-27 20:45:08 -05:00
committed by GitHub
parent a60731247f
commit df04dffade
12 changed files with 242 additions and 210 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
tests/v1/engine/test_engine_core.py
View File

@@ -7,7 +7,6 @@ from transformers import AutoTokenizer
from vllm import SamplingParams
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 import EngineCore
@@ -43,13 +42,11 @@ def test_engine_core(monkeypatch):
m.setenv("VLLM_USE_V1", "1")
"""Setup the EngineCore."""
engine_args = EngineArgs(model=MODEL_NAME)
vllm_config = engine_args.create_engine_config(
usage_context=UsageContext.UNKNOWN_CONTEXT)
vllm_config = engine_args.create_engine_config()
executor_class = AsyncLLM._get_executor_cls(vllm_config)
engine_core = EngineCore(vllm_config=vllm_config,
executor_class=executor_class,
usage_context=UsageContext.UNKNOWN_CONTEXT)
executor_class=executor_class)
"""Test basic request lifecycle."""
# First request.
@@ -151,13 +148,11 @@ def test_engine_core_advanced_sampling(monkeypatch):
m.setenv("VLLM_USE_V1", "1")
"""Setup the EngineCore."""
engine_args = EngineArgs(model=MODEL_NAME)
vllm_config = engine_args.create_engine_config(
usage_context=UsageContext.UNKNOWN_CONTEXT)
vllm_config = engine_args.create_engine_config()
executor_class = AsyncLLM._get_executor_cls(vllm_config)
engine_core = EngineCore(vllm_config=vllm_config,
executor_class=executor_class,
usage_context=UsageContext.UNKNOWN_CONTEXT)
executor_class=executor_class)
"""Test basic request lifecycle."""
# First request.
request: EngineCoreRequest = make_request()

10
tests/v1/engine/test_engine_core_client.py
View File

@@ -86,11 +86,10 @@ def test_engine_core_client(monkeypatch, multiprocessing_mode: bool):
UsageContext.UNKNOWN_CONTEXT)
executor_class = AsyncLLM._get_executor_cls(vllm_config)
client = EngineCoreClient.make_client(
vllm_config,
executor_class,
UsageContext.UNKNOWN_CONTEXT,
multiprocess_mode=multiprocessing_mode,
asyncio_mode=False,
vllm_config=vllm_config,
executor_class=executor_class,
)
MAX_TOKENS = 20
@@ -158,11 +157,10 @@ async def test_engine_core_client_asyncio(monkeypatch):
usage_context=UsageContext.UNKNOWN_CONTEXT)
executor_class = AsyncLLM._get_executor_cls(vllm_config)
client = EngineCoreClient.make_client(
vllm_config,
executor_class,
UsageContext.UNKNOWN_CONTEXT,
multiprocess_mode=True,
asyncio_mode=True,
vllm_config=vllm_config,
executor_class=executor_class,
)
MAX_TOKENS = 20