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 deprecated inference.chat_completion implementations

Browse source 
vllm -
 - requires max_tokens be set, use config value
 - set tool_choice to none if no tools provided
This commit is contained in:
Matthew Farrellee 2025-10-01 11:28:42 -04:00
parent f1748e2f92
commit f754e1b65b
18 changed files with 193 additions and 1411 deletions
Download patch file Download diff file Expand all files Collapse all files

56
llama_stack/providers/remote/inference/runpod/runpod.py
View file

@ -3,9 +3,7 @@
#
# 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
from openai import OpenAI
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.apis.inference import OpenAIEmbeddingsResponse
@ -13,10 +11,7 @@ from llama_stack.apis.inference import OpenAIEmbeddingsResponse
# from llama_stack.providers.datatypes import ModelsProtocolPrivate
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,
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_prompt,
@ -53,7 +48,6 @@ MODEL_ENTRIES = [
class RunpodInferenceAdapter(
ModelRegistryHelper,
Inference,
OpenAIChatCompletionToLlamaStackMixin,
):
def __init__(self, config: RunpodImplConfig) -> None:
ModelRegistryHelper.__init__(self, stack_to_provider_models_map=RUNPOD_SUPPORTED_MODELS)
@ -65,56 +59,6 @@ class RunpodInferenceAdapter(
async def shutdown(self) -> None:
pass
async def chat_completion(
self,
model: str,
messages: list[Message],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
tools: list[ToolDefinition] | None = None,
tool_choice: ToolChoice | None = ToolChoice.auto,
tool_prompt_format: ToolPromptFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
tool_config: ToolConfig | None = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
request = ChatCompletionRequest(
model=model,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
stream=stream,
logprobs=logprobs,
tool_config=tool_config,
)
client = OpenAI(base_url=self.config.url, api_key=self.config.api_token)
if stream:
return self._stream_chat_completion(request, client)
else:
return await self._nonstream_chat_completion(request, client)
async def _nonstream_chat_completion(
self, request: ChatCompletionRequest, client: OpenAI
) -> ChatCompletionResponse:
params = self._get_params(request)
r = client.completions.create(**params)
return process_chat_completion_response(r, request)
async def _stream_chat_completion(self, request: ChatCompletionRequest, client: OpenAI) -> AsyncGenerator:
params = self._get_params(request)
async def _to_async_generator():
s = client.completions.create(**params)
for chunk in s:
yield chunk
stream = _to_async_generator()
async for chunk in process_chat_completion_stream_response(stream, request):
yield chunk
def _get_params(self, request: ChatCompletionRequest) -> dict:
return {
"model": self.map_to_provider_model(request.model),