format

neuralmagic · Nov 1, 2024 · 3c14bdf · 3c14bdf
1 parent 7c977d3
commit 3c14bdf
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 9 deletions.
diff --git a/vllm/entrypoints/llm.py b/vllm/entrypoints/llm.py
@@ -1,5 +1,5 @@
-import time
 import itertools
+import time
 import warnings
 from contextlib import contextmanager
 from typing import (Any, ClassVar, Dict, List, Optional, Sequence, Tuple,
@@ -33,9 +33,9 @@
 from vllm.utils import Counter, deprecate_args, deprecate_kwargs, is_list_of
 
 if envs.VLLM_USE_V1:
-    from vllm.v1.engine.llm_engine import LLMEngine  # type: ignore
     from vllm.v1.engine.core import EngineCoreClient  # type: ignore
     from vllm.v1.engine.detokenizer import Detokenizer  # type: ignore
+    from vllm.v1.engine.llm_engine import LLMEngine  # type: ignore
     from vllm.v1.engine.processor import Processor  # type: ignore
 else:
     from vllm.engine.llm_engine import LLMEngine  # type: ignore
@@ -918,8 +918,8 @@ def _add_request(
         if envs.VLLM_USE_V1:
             # 1) Convert input --> DetokenizerRequest / EngineCoreRequest.
             detokenizer_req, engine_core_req = self.processor.process_inputs(
-                request_id, prompt, params, time.time(), lora_request,
-                None, prompt_adapter_request, priority)
+                request_id, prompt, params, time.time(), lora_request, None,
+                prompt_adapter_request, priority)
 
             # 2) Add the request to Detokenizer (this process).
             self.detokenizer.add_request(detokenizer_req)
@@ -969,9 +969,10 @@ def _run_engine_v1(
                 desc="Processed prompts",
                 dynamic_ncols=True,
             )
-        
+
         # Run the engine.
-        request_outputs: List[Union[RequestOutput, EmbeddingRequestOutput]] = []
+        request_outputs: List[Union[RequestOutput,
+                                    EmbeddingRequestOutput]] = []
         while self.detokenizer.has_unfinished_requests():
             engine_core_outputs = self.engine_core_client.get_output()
             outputs = self.detokenizer.step(engine_core_outputs)
@@ -988,7 +989,6 @@ def _run_engine_v1(
         # its previous requests.
         return sorted(outputs, key=lambda x: int(x.request_id))
 
-
     def _run_engine(
             self, *, use_tqdm: bool
     ) -> List[Union[RequestOutput, EmbeddingRequestOutput]]:

diff --git a/vllm/v1/engine/async_llm_engine.py b/vllm/v1/engine/async_llm_engine.py
@@ -17,8 +17,8 @@
 from vllm.sampling_params import SamplingParams
 from vllm.usage.usage_lib import UsageContext
 from vllm.v1.engine.async_stream import AsyncStream
-from vllm.v1.engine.detokenizer import Detokenizer
 from vllm.v1.engine.core import EngineCoreClient
+from vllm.v1.engine.detokenizer import Detokenizer
 from vllm.v1.engine.processor import Processor
 from vllm.v1.engine.protocol import LLMEngineProtocol
 from vllm.v1.executor.gpu_executor import GPUExecutor

diff --git a/vllm/v1/engine/llm_engine.py b/vllm/v1/engine/llm_engine.py
@@ -15,8 +15,8 @@
 from vllm.prompt_adapter.request import PromptAdapterRequest
 from vllm.sampling_params import SamplingParams
 from vllm.usage.usage_lib import UsageContext
-from vllm.v1.engine.detokenizer import Detokenizer
 from vllm.v1.engine.core import EngineCore
+from vllm.v1.engine.detokenizer import Detokenizer
 from vllm.v1.engine.processor import Processor
 from vllm.v1.engine.protocol import LLMEngineProtocol
 from vllm.v1.executor.gpu_executor import GPUExecutor