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

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 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,