phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: remove /v1/inference/completion and implementations

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-30 03:46:07 -04:00
parent 606f4cf281
commit 4b641d7127
78 changed files with 16143 additions and 17755 deletions
Download patch file Download diff file Expand all files Collapse all files

79
llama_stack/providers/remote/inference/tgi/tgi.py
View file

@ -10,13 +10,9 @@ from collections.abc import AsyncGenerator
from huggingface_hub import AsyncInferenceClient, HfApi
from pydantic import SecretStr
from llama_stack.apis.common.content_types import (
InterleavedContent,
)
from llama_stack.apis.inference import (
ChatCompletionRequest,
ChatCompletionResponse,
CompletionRequest,
Inference,
LogProbConfig,
Message,
@ -44,13 +40,10 @@ from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
process_chat_completion_stream_response,
process_completion_response,
process_completion_stream_response,
)
from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
from llama_stack.providers.utils.inference.prompt_adapter import (
chat_completion_request_to_model_input_info,
completion_request_to_prompt_model_input_info,
)
from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig
@ -122,31 +115,6 @@ class _HfAdapter(
async def unregister_model(self, model_id: str) -> None:
pass
async def completion(
self,
model_id: str,
content: InterleavedContent,
sampling_params: SamplingParams | None = None,
response_format: ResponseFormat | None = None,
stream: bool | None = False,
logprobs: LogProbConfig | None = None,
) -> AsyncGenerator:
if sampling_params is None:
sampling_params = SamplingParams()
model = await self.model_store.get_model(model_id)
request = CompletionRequest(
model=model.provider_resource_id,
content=content,
sampling_params=sampling_params,
response_format=response_format,
stream=stream,
logprobs=logprobs,
)
if stream:
return self._stream_completion(request)
else:
return await self._nonstream_completion(request)
def _get_max_new_tokens(self, sampling_params, input_tokens):
return min(
sampling_params.max_tokens or (self.max_tokens - input_tokens),
@ -180,53 +148,6 @@ class _HfAdapter(
return options
async def _get_params_for_completion(self, request: CompletionRequest) -> dict:
prompt, input_tokens = await completion_request_to_prompt_model_input_info(request)
return dict(
prompt=prompt,
stream=request.stream,
details=True,
max_new_tokens=self._get_max_new_tokens(request.sampling_params, input_tokens),
stop_sequences=["<|eom_id|>", "<|eot_id|>"],
**self._build_options(request.sampling_params, request.response_format),
)
async def _stream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params_for_completion(request)
async def _generate_and_convert_to_openai_compat():
s = await self.hf_client.text_generation(**params)
async for chunk in s:
token_result = chunk.token
finish_reason = None
if chunk.details:
finish_reason = chunk.details.finish_reason
choice = OpenAICompatCompletionChoice(text=token_result.text, finish_reason=finish_reason)
yield OpenAICompatCompletionResponse(
choices=[choice],
)
stream = _generate_and_convert_to_openai_compat()
async for chunk in process_completion_stream_response(stream):
yield chunk
async def _nonstream_completion(self, request: CompletionRequest) -> AsyncGenerator:
params = await self._get_params_for_completion(request)
r = await self.hf_client.text_generation(**params)
choice = OpenAICompatCompletionChoice(
finish_reason=r.details.finish_reason,
text="".join(t.text for t in r.details.tokens),
)
response = OpenAICompatCompletionResponse(
choices=[choice],
)
return process_completion_response(response)
async def chat_completion(
self,
model_id: str,