phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

use task and async generator instead of a thread

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-12 16:41:48 -04:00
parent a673484e21
commit c6403706b4
1 changed files with 10 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

18
llama_stack/testing/inference_recorder.py
View file

@ -378,17 +378,17 @@ def patch_inference_clients():
def patched_models_list(self, *args, **kwargs):
import asyncio
import concurrent.futures
with concurrent.futures.ThreadPoolExecutor() as executor:
future = executor.submit(
lambda: asyncio.run(
_patched_inference_method(
_original_methods["models_list"], self, "openai", "/v1/models", *args, **kwargs
task = asyncio.create_task(
_patched_inference_method(_original_methods["models_list"], self, "openai", "/v1/models", *args, **kwargs)
)
)
)
return future.result()
async def _iter():
result = await task
async for item in result:
yield item
return _iter()
# Apply OpenAI patches
AsyncChatCompletions.create = patched_chat_completions_create