phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 07:30:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add batch inference API to llama stack inference

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-08 13:50:52 -07:00
parent ed58a94b30
commit 0cfb2e2473
24 changed files with 1041 additions and 377 deletions
Download patch file Download diff file Expand all files Collapse all files

40
llama_stack/distribution/routers/routers.py
View file

@ -17,6 +17,8 @@ from llama_stack.apis.datasetio import DatasetIO
from llama_stack.apis.datasets import DatasetPurpose, DataSource
from llama_stack.apis.eval import BenchmarkConfig, Eval, EvaluateResponse, Job
from llama_stack.apis.inference import (
BatchChatCompletionResponse,
BatchCompletionResponse,
ChatCompletionResponse,
ChatCompletionResponseEventType,
ChatCompletionResponseStreamChunk,
@ -334,6 +336,30 @@ class InferenceRouter(Inference):
response.metrics = metrics if response.metrics is None else response.metrics + metrics
return response
async def batch_chat_completion(
self,
model_id: str,
messages_batch: List[List[Message]],
tools: Optional[List[ToolDefinition]] = None,
tool_config: Optional[ToolConfig] = None,
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse:
logger.debug(
f"InferenceRouter.batch_chat_completion: {model_id=}, {len(messages_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
)
provider = 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,
@ -398,6 +424,20 @@ class InferenceRouter(Inference):
response.metrics = metrics if response.metrics is None else response.metrics + metrics
return response
async def batch_completion(
self,
model_id: str,
content_batch: List[InterleavedContent],
sampling_params: Optional[SamplingParams] = None,
response_format: Optional[ResponseFormat] = None,
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse:
logger.debug(
f"InferenceRouter.batch_completion: {model_id=}, {len(content_batch)=}, {sampling_params=}, {response_format=}, {logprobs=}",
)
provider = 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,