phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove batch-related APIs

Browse source 
APIs removed:
 - POST /v1/batch-inference/completion
 - POST /v1/batch-inference/chat-completion
 - POST /v1/inference/batch-completion
 - POST /v1/inference/batch-chat-completion

note -
 - batch-completion & batch-chat-completion were only implemented for inference=inline::meta-reference
 - batch-inference were not implemented
This commit is contained in:
Matthew Farrellee 2025-08-26 15:22:50 -04:00
parent 963305c84d
commit f6d1867bf5
12 changed files with 190 additions and 972 deletions
Download patch file Download diff file Expand all files Collapse all files

40
llama_stack/core/routers/inference.py
View file

@ -20,8 +20,6 @@ from llama_stack.apis.common.content_types import (
)
from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError
from llama_stack.apis.inference import (
BatchChatCompletionResponse,
BatchCompletionResponse,
ChatCompletionResponse,
ChatCompletionResponseEventType,
ChatCompletionResponseStreamChunk,
@ -268,30 +266,6 @@ class InferenceRouter(Inference):
)
return response
async def batch_chat_completion(
self,
model_id: str,
messages_batch: list[list[Message]],
tools: list[ToolDefinition] | None = None,
tool_config: ToolConfig | None = None,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
) -> BatchChatCompletionResponse:
logger.debug(
f"InferenceRouter.batch_chat_completion: {model_id=}, {len(messages_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
)
provider = await self.routing_table.get_provider_impl(model_id)
return await provider.batch_chat_completion(
model_id=model_id,
messages_batch=messages_batch,
tools=tools,
tool_config=tool_config,
sampling_params=sampling_params,
response_format=response_format,
logprobs=logprobs,
)
async def completion(
self,
model_id: str,
@ -333,20 +307,6 @@ class InferenceRouter(Inference):
return response
async def batch_completion(
self,
model_id: str,
content_batch: list[InterleavedContent],
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
logprobs: LogProbConfig | None = None,
) -> BatchCompletionResponse:
logger.debug(
f"InferenceRouter.batch_completion: {model_id=}, {len(content_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
)
provider = await self.routing_table.get_provider_impl(model_id)
return await provider.batch_completion(model_id, content_batch, sampling_params, response_format, logprobs)
async def embeddings(
self,
model_id: str,