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

[CI/Build] Update Ruff version (#8469)

Browse Source 
Signed-off-by: Aaron Pham <contact@aarnphm.xyz>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
This commit is contained in:
Aaron Pham
2024-09-18 07:00:56 -04:00
committed by GitHub
parent 6ffa3f314c
commit 9d104b5beb
27 changed files with 50 additions and 77 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
vllm/engine/async_llm_engine.py
View File

@@ -826,7 +826,7 @@ class AsyncLLMEngine:
request_id: The unique id of the request.
lora_request: LoRA request to use for generation, if any.
trace_headers: OpenTelemetry trace headers.
prompt_adapter_request: Prompt Adapter request to use
prompt_adapter_request: Prompt Adapter request to use
for generation, if any.
Yields:
@@ -1042,7 +1042,7 @@ class AsyncLLMEngine:
async def start_profile(self) -> None:
# using type instead of isinstance to check to avoid capturing
# inherited classes
if type(self.engine.model_executor) == GPUExecutorAsync:
if type(self.engine.model_executor) == GPUExecutorAsync: # noqa: E721
self.engine.model_executor.start_profile()
else:
self.engine.model_executor._run_workers("start_profile")
@@ -1050,7 +1050,7 @@ class AsyncLLMEngine:
async def stop_profile(self) -> None:
# using type instead of isinstance to check to avoid capturing
# inherited classes
if type(self.engine.model_executor) == GPUExecutorAsync:
if type(self.engine.model_executor) == GPUExecutorAsync: # noqa: E721
self.engine.model_executor.stop_profile()
else:
self.engine.model_executor._run_workers("stop_profile")