phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 03:29:59 +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

22
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -526,3 +526,25 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
user=user,
)
return await self.client.chat.completions.create(**params) # type: ignore
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,
):
raise NotImplementedError("Batch completion is not supported for Ollama")
async def batch_chat_completion(
self,
model_id: str,
messages_batch: List[List[Message]],
sampling_params: Optional[SamplingParams] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_config: Optional[ToolConfig] = None,
response_format: Optional[ResponseFormat] = None,
logprobs: Optional[LogProbConfig] = None,
):
raise NotImplementedError("Batch chat completion is not supported for Ollama")