phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-09 11:20:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

inference registry updates

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-05 22:25:48 -07:00 • committed by Ashwin Bharambe
parent 4215cc9331
commit 59302a86df
12 changed files with 570 additions and 535 deletions
Download patch file Download diff file Expand all files Collapse all files

6
llama_stack/providers/adapters/inference/fireworks/fireworks.py
View file

@ -13,7 +13,7 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.datatypes import Message, StopReason
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.providers.utils.inference.routable import RoutableProviderForModels
from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.augment_messages import (
@ -30,9 +30,9 @@ FIREWORKS_SUPPORTED_MODELS = {
}
class FireworksInferenceAdapter(Inference, RoutableProviderForModels):
class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
def __init__(self, config: FireworksImplConfig) -> None:
RoutableProviderForModels.__init__(
ModelRegistryHelper.__init__(
self, stack_to_provider_models_map=FIREWORKS_SUPPORTED_MODELS
)
self.config = config