20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix typing in AsyncLLMEngine & add toml to requirements-dev (#2100)

Browse Source
This commit is contained in:
mezuzza 2023-12-14 03:19:41 -05:00 committed by GitHub
parent 31c1f3255e
commit 6774bd50b0
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
2 changed files with 8 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
requirements-dev.txt
View File

@ -1,5 +1,6 @@
# formatting # formatting
yapf==0.32.0 yapf==0.32.0
toml==0.10.2
ruff==0.1.5 ruff==0.1.5
# type checking # type checking

5
vllm/engine/async_llm_engine.py
View File

@ -2,7 +2,7 @@ import asyncio
import time import time
from functools import partial from functools import partial
from typing import (Any, Dict, Iterable, List, Optional, Set, Tuple, Type, from typing import (Any, Dict, Iterable, List, Optional, Set, Tuple, Type,
Union) Union, AsyncIterator)
from vllm.config import ModelConfig from vllm.config import ModelConfig
from vllm.engine.arg_utils import AsyncEngineArgs from vllm.engine.arg_utils import AsyncEngineArgs
@ -405,7 +405,8 @@ class AsyncLLMEngine:
prompt: Optional[str], prompt: Optional[str],
sampling_params: SamplingParams, sampling_params: SamplingParams,
request_id: str, request_id: str,
prompt_token_ids: Optional[List[int]] = None) -> RequestOutput: prompt_token_ids: Optional[List[int]] = None
) -> AsyncIterator[RequestOutput]:
"""Generate outputs for a request. """Generate outputs for a request.
Generate outputs for a request. This method is a coroutine. It adds the Generate outputs for a request. This method is a coroutine. It adds the