mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
314ee09ae3
llama-models should have extremely minimal cruft. Its sole purpose should be didactic -- show the simplest implementation of the llama models and document the prompt formats, etc. This PR is the complement to https://github.com/meta-llama/llama-models/pull/279 ## Test Plan Ensure all `llama` CLI `model` sub-commands work: ```bash llama model list llama model download --model-id ... llama model prompt-format -m ... ``` Ran tests: ```bash cd tests/client-sdk LLAMA_STACK_CONFIG=fireworks pytest -s -v inference/ LLAMA_STACK_CONFIG=fireworks pytest -s -v vector_io/ LLAMA_STACK_CONFIG=fireworks pytest -s -v agents/ ``` Create a fresh venv `uv venv && source .venv/bin/activate` and run `llama stack build --template fireworks --image-type venv` followed by `llama stack run together --image-type venv` <-- the server runs Also checked that the OpenAPI generator can run and there is no change in the generated files as a result. ```bash cd docs/openapi_generator sh run_openapi_generator.sh ```
60 lines
1.9 KiB
Python
60 lines
1.9 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import List, Optional, Protocol, runtime_checkable
|
|
|
|
from pydantic import BaseModel
|
|
|
|
from llama_stack.apis.inference import (
|
|
ChatCompletionResponse,
|
|
CompletionResponse,
|
|
InterleavedContent,
|
|
LogProbConfig,
|
|
Message,
|
|
ResponseFormat,
|
|
SamplingParams,
|
|
ToolChoice,
|
|
ToolDefinition,
|
|
ToolPromptFormat,
|
|
)
|
|
from llama_stack.schema_utils import json_schema_type, webmethod
|
|
|
|
|
|
@json_schema_type
|
|
class BatchCompletionResponse(BaseModel):
|
|
batch: List[CompletionResponse]
|
|
|
|
|
|
@json_schema_type
|
|
class BatchChatCompletionResponse(BaseModel):
|
|
batch: List[ChatCompletionResponse]
|
|
|
|
|
|
@runtime_checkable
|
|
class BatchInference(Protocol):
|
|
@webmethod(route="/batch-inference/completion", method="POST")
|
|
async def batch_completion(
|
|
self,
|
|
model: str,
|
|
content_batch: List[InterleavedContent],
|
|
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
|
response_format: Optional[ResponseFormat] = None,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchCompletionResponse: ...
|
|
|
|
@webmethod(route="/batch-inference/chat-completion", method="POST")
|
|
async def batch_chat_completion(
|
|
self,
|
|
model: str,
|
|
messages_batch: List[List[Message]],
|
|
sampling_params: Optional[SamplingParams] = SamplingParams(),
|
|
# zero-shot tool definitions as input to the model
|
|
tools: Optional[List[ToolDefinition]] = list,
|
|
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
|
|
tool_prompt_format: Optional[ToolPromptFormat] = None,
|
|
response_format: Optional[ResponseFormat] = None,
|
|
logprobs: Optional[LogProbConfig] = None,
|
|
) -> BatchChatCompletionResponse: ...
|