phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 03:19:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Another round of simplification and clarity for models/shields/memory_banks stuff

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-09 19:19:26 -07:00
parent 73a0a34e39
commit b55034c0de
27 changed files with 454 additions and 444 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/apis/batch_inference/batch_inference.py
View file

@ -4,7 +4,7 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import List, Optional, Protocol
from typing import List, Optional, Protocol, runtime_checkable
from llama_models.schema_utils import json_schema_type, webmethod
@ -47,6 +47,7 @@ class BatchChatCompletionResponse(BaseModel):
completion_message_batch: List[CompletionMessage]
@runtime_checkable
class BatchInference(Protocol):
@webmethod(route="/batch_inference/completion")
async def batch_completion(