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

13
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -14,7 +14,6 @@ from llama_stack.apis.inference import OpenAIEmbeddingsResponse
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, build_hf_repo_model_entry
from llama_stack.providers.utils.inference.openai_compat import (
OpenAIChatCompletionToLlamaStackMixin,
OpenAICompletionToLlamaStackMixin,
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
@ -55,7 +54,6 @@ class RunpodInferenceAdapter(
ModelRegistryHelper,
Inference,
OpenAIChatCompletionToLlamaStackMixin,
OpenAICompletionToLlamaStackMixin,
):
def __init__(self, config: RunpodImplConfig) -> None:
ModelRegistryHelper.__init__(self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS)
@ -67,17 +65,6 @@ class RunpodInferenceAdapter(
async def shutdown(self) -> None:
pass
async def completion(
self,
model: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> AsyncGenerator:
raise NotImplementedError()
async def chat_completion(
self,
model: str,