phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-03 09:53:45 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: implement OpenAI chat completion for meta_reference provider

Browse source 
- Add chat_completion() method to LlamaGenerator supporting OpenAI request format
- Implement openai_chat_completion() in MetaReferenceInferenceImpl
- Fix ModelRunner task dispatch to handle chat_completion tasks
- Add convert_openai_message_to_raw_message() utility for message conversion
- Add unit tests for message conversion and model-parallel dispatch
- Remove unused CompletionRequestWithRawContent references

Signed-off-by: Charlie Doern <cdoern@redhat.com>
This commit is contained in:
Charlie Doern 2025-11-08 14:24:13 -05:00
parent 54754cb2a7
commit 7574f147b6
8 changed files with 240 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

5
tests/unit/providers/inline/inference/__init__.py Normal file
View file

@ -0,0 +1,5 @@
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.