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

Support for Llama3.2 models and Swift SDK (#98)

Browse source
This commit is contained in:
Ashwin Bharambe 2024-09-25 10:29:58 -07:00 • committed by GitHub
parent 95abbf576b
commit 56aed59eb4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
56 changed files with 3745 additions and 630 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/impls/meta_reference/inference/inference.py
View file

@ -21,7 +21,9 @@ from llama_stack.apis.inference import (
ToolCallDelta,
ToolCallParseStatus,
)
from llama_stack.providers.utils.inference.prepare_messages import prepare_messages
from llama_stack.providers.utils.inference.augment_messages import (
augment_messages_for_tools,
)
from .config import MetaReferenceImplConfig
from .model_parallel import LlamaModelParallelGenerator
@ -57,7 +59,7 @@ class MetaReferenceInferenceImpl(Inference):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
tools: Optional[List[ToolDefinition]] = [],
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
stream: Optional[bool] = False,
@ -70,14 +72,14 @@ class MetaReferenceInferenceImpl(Inference):
model=model,
messages=messages,
sampling_params=sampling_params,
tools=tools,
tools=tools or [],
tool_choice=tool_choice,
tool_prompt_format=tool_prompt_format,
stream=stream,
logprobs=logprobs,
)
messages = prepare_messages(request)
messages = augment_messages_for_tools(request)
model = resolve_model(request.model)
if model is None:
raise RuntimeError(