phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Remove request wrapper migration (#64)

Browse source 
* [1/n] migrate inference/chat_completion

* migrate inference/completion

* inference/completion

* inference regenerate openapi spec

* safety api

* migrate agentic system

* migrate apis without implementations

* re-generate openapi spec

* remove hack from openapi generator

* fix inference

* fix inference

* openapi generator rerun

* Simplified Telemetry API and tying it to logger (#57)

* Simplified Telemetry API and tying it to logger

* small update which adds a METRIC type

* move span events one level down into structured log events

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

* fix api to work with openapi generator

* fix agentic calling inference

* together adapter inference

* update inference adapters

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
This commit is contained in:
Xi Yan 2024-09-12 15:03:49 -07:00 • committed by GitHub
parent 1d0e91d802
commit 5712566061
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 1211 additions and 3031 deletions
Download patch file Download diff file Expand all files Collapse all files

25
llama_toolchain/inference/meta_reference/inference.py
View file

@ -22,9 +22,12 @@ from llama_toolchain.inference.api import (
ToolCallParseStatus,
)
from llama_toolchain.inference.prepare_messages import prepare_messages
from .config import MetaReferenceImplConfig
from .model_parallel import LlamaModelParallelGenerator
from llama_models.llama3.api.datatypes import * # noqa: F403
from llama_toolchain.inference.api import * # noqa: F403
# there's a single model parallel process running serving the model. for now,
# we don't support multiple concurrent requests to this process.
@ -50,10 +53,30 @@ class MetaReferenceInferenceImpl(Inference):
# hm, when stream=False, we should not be doing SSE :/ which is what the
# top-level server is going to do. make the typing more specific here
async def chat_completion(
self, request: ChatCompletionRequest
self,
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = list(),
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncIterator[
Union[ChatCompletionResponseStreamChunk, ChatCompletionResponse]
]:
# wrapper request to make it easier to pass around (internal only, not exposed to API)
request = ChatCompletionRequest(
model=model,
messages=messages,
sampling_params=sampling_params,
tools=tools,
tool_choice=tool_choice,
tool_prompt_format=tool_prompt_format,
stream=stream,
logprobs=logprobs,
)
messages = prepare_messages(request)
model = resolve_model(request.model)
if model is None: