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

61
llama_stack/providers/remote/inference/cerebras/cerebras.py
View file

@ -4,7 +4,6 @@
# 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 urllib.parse import urljoin
from cerebras.cloud.sdk import AsyncCerebras
@ -12,17 +11,8 @@ from cerebras.cloud.sdk import AsyncCerebras
from llama_stack.apis.inference import (
ChatCompletionRequest,
CompletionRequest,
CompletionResponse,
Inference,
LogProbConfig,
Message,
OpenAIEmbeddingsResponse,
ResponseFormat,
SamplingParams,
ToolChoice,
ToolConfig,
ToolDefinition,
ToolPromptFormat,
TopKSamplingStrategy,
)
from llama_stack.providers.utils.inference.model_registry import (
@ -30,8 +20,6 @@ from llama_stack.providers.utils.inference.model_registry import (
)
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
)
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from llama_stack.providers.utils.inference.prompt_adapter import (
@ -68,55 +56,6 @@ class CerebrasInferenceAdapter(
async def shutdown(self) -> None:
pass
async def chat_completion(
self,
model_id: str,
messages: list[Message],
sampling_params: SamplingParams | None = None,
tools: list[ToolDefinition] | None = None,
tool_choice: ToolChoice | None = ToolChoice.auto,
tool_prompt_format: ToolPromptFormat | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
tool_config: ToolConfig | None = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
model = await self.model_store.get_model(model_id)
request = ChatCompletionRequest(
model=model.provider_resource_id,
messages=messages,
sampling_params=sampling_params,
tools=tools or [],
tool_choice=tool_choice,
tool_prompt_format=tool_prompt_format,
response_format=response_format,
stream=stream,
logprobs=logprobs,
tool_config=tool_config,
)
if stream:
return self._stream_chat_completion(request)
else:
return await self._nonstream_chat_completion(request)
async def _nonstream_chat_completion(self, request: CompletionRequest) -> CompletionResponse:
params = await self._get_params(request)
r = await self._cerebras_client.completions.create(**params)
return process_chat_completion_response(r, request)
async def _stream_chat_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params(request)
stream = await self._cerebras_client.completions.create(**params)
async for chunk in process_chat_completion_stream_response(stream, request):
yield chunk
async def _get_params(self, request: ChatCompletionRequest | CompletionRequest) -> dict:
if request.sampling_params and isinstance(request.sampling_params.strategy, TopKSamplingStrategy):
raise ValueError("`top_k` not supported by Cerebras")