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

Inference to use provider resource id to register and validate (#428)

Browse source 
This PR changes the way model id gets translated to the final model name
that gets passed through the provider.
Major changes include:
1) Providers are responsible for registering an object and as part of
the registration returning the object with the correct provider specific
name of the model provider_resource_id
2) To help with the common look ups different names a new ModelLookup
class is created.



Tested all inference providers including together, fireworks, vllm,
ollama, meta reference and bedrock
This commit is contained in:
Dinesh Yeduguru 2024-11-12 20:02:00 -08:00 • committed by GitHub
parent e51107e019
commit fdff24e77a
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
21 changed files with 460 additions and 290 deletions
Download patch file Download diff file Expand all files Collapse all files

30
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -6,6 +6,8 @@
from typing import AsyncGenerator
from llama_models.datatypes import CoreModelId
from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message
@ -15,7 +17,10 @@ from openai import OpenAI
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.providers.utils.inference.model_registry import (
build_model_alias,
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
get_sampling_options,
process_chat_completion_response,
@ -28,16 +33,23 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
from .config import DatabricksImplConfig
DATABRICKS_SUPPORTED_MODELS = {
"Llama3.1-70B-Instruct": "databricks-meta-llama-3-1-70b-instruct",
"Llama3.1-405B-Instruct": "databricks-meta-llama-3-1-405b-instruct",
}
model_aliases = [
build_model_alias(
"databricks-meta-llama-3-1-70b-instruct",
CoreModelId.llama3_1_70b_instruct.value,
),
build_model_alias(
"databricks-meta-llama-3-1-405b-instruct",
CoreModelId.llama3_1_405b_instruct.value,
),
]
class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
def __init__(self, config: DatabricksImplConfig) -> None:
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=DATABRICKS_SUPPORTED_MODELS
self,
model_aliases=model_aliases,
)
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())
@ -113,8 +125,10 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
def _get_params(self, request: ChatCompletionRequest) -> dict:
return {
"model": self.map_to_provider_model(request.model),
"prompt": chat_completion_request_to_prompt(request, self.formatter),
"model": request.model,
"prompt": chat_completion_request_to_prompt(
request, self.get_llama_model(request.model), self.formatter
),
"stream": request.stream,
**get_sampling_options(request.sampling_params),
}