phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 02:52:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fixes for all providers

Browse source
This commit is contained in:
Dinesh Yeduguru 2024-11-12 14:25:28 -08:00
parent d5874735ea
commit 948f6ece6e
8 changed files with 133 additions and 135 deletions
Download patch file Download diff file Expand all files Collapse all files

23
llama_stack/providers/remote/inference/bedrock/bedrock.py
View file

@ -13,7 +13,7 @@ from llama_models.llama3.api.chat_format import ChatFormat
from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
@ -24,20 +24,17 @@ from llama_stack.providers.utils.bedrock.client import create_bedrock_client
model_aliases = [
ModelAlias(
provider_model_id="meta.llama3-1-8b-instruct-v1:0",
aliases=["Llama3.1-8B-Instruct"],
llama_model=CoreModelId.llama3_1_8b_instruct,
build_model_alias(
"meta.llama3-1-8b-instruct-v1:0",
CoreModelId.llama3_1_8b_instruct,
),
ModelAlias(
provider_model_id="meta.llama3-1-70b-instruct-v1:0",
aliases=["Llama3.1-70B-Instruct"],
llama_model=CoreModelId.llama3_1_70b_instruct,
build_model_alias(
"meta.llama3-1-70b-instruct-v1:0",
CoreModelId.llama3_1_70b_instruct,
),
ModelAlias(
provider_model_id="meta.llama3-1-405b-instruct-v1:0",
aliases=["Llama3.1-405B-Instruct"],
llama_model=CoreModelId.llama3_1_405b_instruct,
build_model_alias(
"meta.llama3-1-405b-instruct-v1:0",
CoreModelId.llama3_1_405b_instruct,
),
]

16
llama_stack/providers/remote/inference/databricks/databricks.py
View file

@ -18,7 +18,7 @@ from openai import OpenAI
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
@ -34,15 +34,13 @@ from .config import DatabricksImplConfig
model_aliases = [
ModelAlias(
provider_model_id="databricks-meta-llama-3-1-70b-instruct",
aliases=["Llama3.1-70B-Instruct"],
llama_model=CoreModelId.llama3_1_70b_instruct.value,
build_model_alias(
"databricks-meta-llama-3-1-70b-instruct",
CoreModelId.llama3_1_70b_instruct,
),
ModelAlias(
provider_model_id="databricks-meta-llama-3-1-405b-instruct",
aliases=["Llama3.1-405B-Instruct"],
llama_model=CoreModelId.llama3_1_405b_instruct.value,
build_model_alias(
"databricks-meta-llama-3-1-405b-instruct",
CoreModelId.llama3_1_405b_instruct,
),
]

65
llama_stack/providers/remote/inference/fireworks/fireworks.py
View file

@ -15,7 +15,7 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
@ -36,50 +36,41 @@ from .config import FireworksImplConfig
model_aliases = [
ModelAlias(
provider_model_id="fireworks/llama-v3p1-8b-instruct",
aliases=["Llama3.1-8B-Instruct"],
llama_model=CoreModelId.llama3_1_8b_instruct.value,
build_model_alias(
"fireworks/llama-v3p1-8b-instruct",
CoreModelId.llama3_1_8b_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p1-70b-instruct",
aliases=["Llama3.1-70B-Instruct"],
llama_model=CoreModelId.llama3_1_70b_instruct.value,
build_model_alias(
"fireworks/llama-v3p1-70b-instruct",
CoreModelId.llama3_1_70b_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p1-405b-instruct",
aliases=["Llama3.1-405B-Instruct"],
llama_model=CoreModelId.llama3_1_405b_instruct.value,
build_model_alias(
"fireworks/llama-v3p1-405b-instruct",
CoreModelId.llama3_1_405b_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p2-1b-instruct",
aliases=["Llama3.2-1B-Instruct"],
llama_model=CoreModelId.llama3_2_3b_instruct.value,
build_model_alias(
"fireworks/llama-v3p2-1b-instruct",
CoreModelId.llama3_2_3b_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p2-3b-instruct",
aliases=["Llama3.2-3B-Instruct"],
llama_model=CoreModelId.llama3_2_11b_vision_instruct.value,
build_model_alias(
"fireworks/llama-v3p2-3b-instruct",
CoreModelId.llama3_2_11b_vision_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p2-11b-vision-instruct",
aliases=["Llama3.2-11B-Vision-Instruct"],
llama_model=CoreModelId.llama3_2_11b_vision_instruct.value,
build_model_alias(
"fireworks/llama-v3p2-11b-vision-instruct",
CoreModelId.llama3_2_11b_vision_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-v3p2-90b-vision-instruct",
aliases=["Llama3.2-90B-Vision-Instruct"],
llama_model=CoreModelId.llama3_2_90b_vision_instruct.value,
build_model_alias(
"fireworks/llama-v3p2-90b-vision-instruct",
CoreModelId.llama3_2_90b_vision_instruct,
),
ModelAlias(
provider_model_id="fireworks/llama-guard-3-8b",
aliases=["Llama-Guard-3-8B"],
llama_model=CoreModelId.llama_guard_3_8b.value,
build_model_alias(
"fireworks/llama-guard-3-8b",
CoreModelId.llama_guard_3_8b,
),
ModelAlias(
provider_model_id="fireworks/llama-guard-3-11b-vision",
aliases=["Llama-Guard-3-11B-Vision"],
llama_model=CoreModelId.llama_guard_3_11b_vision.value,
build_model_alias(
"fireworks/llama-guard-3-11b-vision",
CoreModelId.llama_guard_3_11b_vision,
),
]

51
llama_stack/providers/remote/inference/ollama/ollama.py
View file

@ -15,7 +15,7 @@ from llama_models.llama3.api.tokenizer import Tokenizer
from ollama import AsyncClient
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
@ -40,40 +40,33 @@ from llama_stack.providers.utils.inference.prompt_adapter import (
model_aliases = [
ModelAlias(
provider_model_id="llama3.1:8b-instruct-fp16",
aliases=["Llama3.1-8B-Instruct"],
llama_model=CoreModelId.llama3_1_8b_instruct.value,
build_model_alias(
"llama3.1:8b-instruct-fp16",
CoreModelId.llama3_1_8b_instruct,
),
ModelAlias(
provider_model_id="llama3.1:70b-instruct-fp16",
aliases=["Llama3.1-70B-Instruct"],
llama_model=CoreModelId.llama3_1_70b_instruct.value,
build_model_alias(
"llama3.1:70b-instruct-fp16",
CoreModelId.llama3_1_70b_instruct,
),
ModelAlias(
provider_model_id="llama3.2:1b-instruct-fp16",
aliases=["Llama3.2-1B-Instruct"],
llama_model=CoreModelId.llama3_2_1b_instruct.value,
build_model_alias(
"llama3.2:1b-instruct-fp16",
CoreModelId.llama3_2_1b_instruct,
),
ModelAlias(
provider_model_id="llama3.2:3b-instruct-fp16",
aliases=["Llama3.2-3B-Instruct"],
llama_model=CoreModelId.llama3_2_3b_instruct.value,
build_model_alias(
"llama3.2:3b-instruct-fp16",
CoreModelId.llama3_2_3b_instruct,
),
ModelAlias(
provider_model_id="llama-guard3:8b",
aliases=["Llama-Guard-3-8B"],
llama_model=CoreModelId.llama_guard_3_8b.value,
build_model_alias(
"llama-guard3:8b",
CoreModelId.llama_guard_3_8b,
),
ModelAlias(
provider_model_id="llama-guard3:1b",
aliases=["Llama-Guard-3-1B"],
llama_model=CoreModelId.llama_guard_3_1b.value,
build_model_alias(
"llama-guard3:1b",
CoreModelId.llama_guard_3_1b,
),
ModelAlias(
provider_model_id="x/llama3.2-vision:11b-instruct-fp16",
aliases=["Llama3.2-11B-Vision-Instruct"],
llama_model=CoreModelId.llama3_2_11b_vision_instruct.value,
build_model_alias(
"x/llama3.2-vision:11b-instruct-fp16",
CoreModelId.llama3_2_11b_vision_instruct,
),
]

58
llama_stack/providers/remote/inference/together/together.py
View file

@ -18,7 +18,7 @@ from together import Together
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.distribution.request_headers import NeedsRequestProviderData
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
@ -39,45 +39,37 @@ from .config import TogetherImplConfig
model_aliases = [
ModelAlias(
provider_model_id="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
aliases=["Llama3.1-8B-Instruct"],
llama_model=CoreModelId.llama3_1_8b_instruct.value,
build_model_alias(
"meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
CoreModelId.llama3_1_8b_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
aliases=["Llama3.1-70B-Instruct"],
llama_model=CoreModelId.llama3_1_70b_instruct.value,
build_model_alias(
"meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo",
CoreModelId.llama3_1_70b_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
aliases=["Llama3.1-405B-Instruct"],
llama_model=CoreModelId.llama3_1_405b_instruct.value,
build_model_alias(
"meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo",
CoreModelId.llama3_1_405b_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Llama-3.2-3B-Instruct-Turbo",
aliases=["Llama3.2-3B-Instruct"],
llama_model=CoreModelId.llama3_2_3b_instruct.value,
build_model_alias(
"meta-llama/Llama-3.2-3B-Instruct-Turbo",
CoreModelId.llama3_2_3b_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
aliases=["Llama3.2-11B-Vision-Instruct"],
llama_model=CoreModelId.llama3_2_11b_vision_instruct.value,
build_model_alias(
"meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo",
CoreModelId.llama3_2_11b_vision_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
aliases=["Llama3.2-90B-Vision-Instruct"],
llama_model=CoreModelId.llama3_2_90b_vision_instruct.value,
build_model_alias(
"meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo",
CoreModelId.llama3_2_90b_vision_instruct,
),
ModelAlias(
provider_model_id="meta-llama/Meta-Llama-Guard-3-8B",
aliases=["Llama-Guard-3-8B"],
llama_model=CoreModelId.llama_guard_3_8b.value,
build_model_alias(
"meta-llama/Meta-Llama-Guard-3-8B",
CoreModelId.llama_guard_3_8b,
),
ModelAlias(
provider_model_id="meta-llama/Llama-Guard-3-11B-Vision-Turbo",
aliases=["Llama-Guard-3-11B-Vision"],
llama_model=CoreModelId.llama_guard_3_11b_vision.value,
build_model_alias(
"meta-llama/Llama-Guard-3-11B-Vision-Turbo",
CoreModelId.llama_guard_3_11b_vision,
),
]

14
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -16,7 +16,7 @@ from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (
ModelAlias,
build_model_alias,
ModelRegistryHelper,
)
from llama_stack.providers.utils.inference.openai_compat import (
@ -36,10 +36,9 @@ from .config import VLLMInferenceAdapterConfig
def build_model_aliases():
return [
ModelAlias(
provider_model_id=model.huggingface_repo,
aliases=[model.descriptor()],
llama_model=model.descriptor(),
build_model_alias(
model.huggingface_repo,
model.core_model_id,
)
for model in all_registered_models()
if model.huggingface_repo
@ -55,11 +54,6 @@ class VLLMInferenceAdapter(Inference, ModelRegistryHelper, ModelsProtocolPrivate
self.config = config
self.formatter = ChatFormat(Tokenizer.get_instance())
self.client = None
self.huggingface_repo_to_llama_model_id = {
model.huggingface_repo: model.descriptor()
for model in all_registered_models()
if model.huggingface_repo
}
async def initialize(self) -> None:
self.client = OpenAI(base_url=self.config.url, api_key=self.config.api_token)