phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

getting closer to a distro definition, distro install + configure works

Browse source
This commit is contained in:
Ashwin Bharambe 2024-08-01 22:59:11 -07:00
parent dac2b5a1ed
commit 041cafbee3
11 changed files with 471 additions and 130 deletions
Download patch file Download diff file Expand all files Collapse all files

9
llama_toolchain/inference/inference.py
View file

@ -16,8 +16,8 @@ from .api.datatypes import (
ToolCallParseStatus,
)
from .api.endpoints import (
ChatCompletionResponse,
ChatCompletionRequest,
ChatCompletionResponse,
ChatCompletionResponseStreamChunk,
CompletionRequest,
Inference,
@ -25,6 +25,13 @@ from .api.endpoints import (
from .model_parallel import LlamaModelParallelGenerator
def get_adapter_impl(config: InlineImplConfig) -> Inference:
assert isinstance(
config, InlineImplConfig
), f"Unexpected config type: {type(config)}"
return InferenceImpl(config)
class InferenceImpl(Inference):
def __init__(self, config: InlineImplConfig) -> None: