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

This commit is contained in:
mezuzza
2023-12-14 00:19:41 -08:00
committed by GitHub
parent 31c1f3255e
commit 6774bd50b0
2 changed files with 8 additions and 6 deletions
+1
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
+7 -6
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
@@ -401,11 +401,12 @@ class AsyncLLMEngine:
return stream return stream
async def generate( async def generate(
self, self,
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