phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-29 07:14:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

second round of feedback

Browse source
This commit is contained in:
dltn 2024-10-09 11:56:02 -07:00
parent fd41ddf733
commit da47273dd1
1 changed files with 1 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/impls/meta_reference/inference/parallel_utils.py
View file

@ -56,28 +56,24 @@ class ReadyRequest(BaseModel):
type: Literal[ProcessingMessageName.ready_request] = (
ProcessingMessageName.ready_request
)
message: str = "READY?"
class ReadyResponse(BaseModel):
type: Literal[ProcessingMessageName.ready_response] = (
ProcessingMessageName.ready_response
)
message: str = "YES READY"
class EndSentinel(BaseModel):
type: Literal[ProcessingMessageName.end_sentinel] = (
ProcessingMessageName.end_sentinel
)
message: str = "__end_sentinel__"
class CancelSentinel(BaseModel):
type: Literal[ProcessingMessageName.cancel_sentinel] = (
ProcessingMessageName.cancel_sentinel
)
message: str = "__cancel_sentinel__"
class TaskRequest(BaseModel):
@ -143,7 +139,7 @@ def retrieve_requests(reply_socket_url: str):
reply_socket.send_multipart([client_id, encode_msg(ready_response)])
break
def send_obj(obj: Union[ProcessingMessage, BaseModel]):
def send_obj(obj: ProcessingMessage):
reply_socket.send_multipart([client_id, encode_msg(obj)])
while True: