phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Fix python3.10 async

Browse source
This commit is contained in:
Neil Mehta 2025-03-18 15:53:41 -04:00 • committed by Matt Clayton
parent aa9562e104
commit 302d72cc47
1 changed files with 10 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

15
llama_stack/providers/remote/inference/lmstudio/_client.py
View file

@ -94,7 +94,6 @@ class LMStudioClient:
chat = self._convert_message_list_to_lmstudio_chat(messages)
config = self._get_completion_config_from_params(sampling_params)
if stream:
async def stream_generator():
prediction_stream = await asyncio.to_thread(
llm.respond_stream,
@ -209,7 +208,6 @@ class LMStudioClient:
) -> Union[CompletionResponse, AsyncIterator[CompletionResponseStreamChunk]]:
config = self._get_completion_config_from_params(sampling_params)
if stream:
async def stream_generator():
prediction_stream = await asyncio.to_thread(
llm.complete_stream,
@ -308,11 +306,18 @@ class LMStudioClient:
async def _async_iterate(self, iterable):
iterator = iter(iterable)
while True:
def safe_next(it):
try:
yield await asyncio.to_thread(next, iterator)
except:
return (next(it), False)
except StopIteration:
return (None, True)
while True:
item, done = await asyncio.to_thread(safe_next, iterator)
if done:
break
yield item
async def _convert_request_to_rest_call(
self, request: ChatCompletionRequest