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

chore: remove /v1/inference/completion and implementations (#3622)

Browse source 
# What does this PR do?

the /inference/completion route is gone. this removes the
implementations.

## Test Plan

ci
This commit is contained in:
Matthew Farrellee 2025-10-01 11:36:53 -04:00 • committed by GitHub
parent ea15f2a270
commit f7c5ef4ec0
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
75 changed files with 16141 additions and 17056 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_stack/providers/utils/inference/litellm_openai_mixin.py
View file

@ -4,14 +4,11 @@
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from collections.abc import AsyncGenerator, AsyncIterator
from collections.abc import AsyncIterator
from typing import Any
import litellm
from llama_stack.apis.common.content_types import (
InterleavedContent,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
@ -108,17 +105,6 @@ class LiteLLMOpenAIMixin(
else model_id
)
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> AsyncGenerator:
raise NotImplementedError("LiteLLM does not support completion requests")
async def chat_completion(
self,
model_id: str,