phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-11 20:40:40 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

revert indent changes on inference.py

Browse source
This commit is contained in:
Honglin Cao 2025-03-11 16:43:34 -04:00
parent e2290a0096
commit 2fb79814ef
1 changed files with 35 additions and 50 deletions
Download patch file Download diff file Expand all files Collapse all files

85
llama_stack/providers/registry/inference.py
View file

@ -34,19 +34,20 @@ def available_providers() -> List[ProviderSpec]:
provider_type="inline::meta-reference", provider_type="inline::meta-reference",
pip_packages=META_REFERENCE_DEPS, pip_packages=META_REFERENCE_DEPS,
module="llama_stack.providers.inline.inference.meta_reference", module="llama_stack.providers.inline.inference.meta_reference",
config_class= config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
"llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
), ),
InlineProviderSpec( InlineProviderSpec(
api=Api.inference, api=Api.inference,
provider_type="inline::meta-reference-quantized", provider_type="inline::meta-reference-quantized",
pip_packages=(META_REFERENCE_DEPS + [ pip_packages=(
"fbgemm-gpu", META_REFERENCE_DEPS
"torchao==0.5.0", + [
]), "fbgemm-gpu",
"torchao==0.5.0",
]
),
module="llama_stack.providers.inline.inference.meta_reference", module="llama_stack.providers.inline.inference.meta_reference",
config_class= config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
"llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
), ),
InlineProviderSpec( InlineProviderSpec(
api=Api.inference, api=Api.inference,
@ -55,8 +56,7 @@ def available_providers() -> List[ProviderSpec]:
"vllm", "vllm",
], ],
module="llama_stack.providers.inline.inference.vllm", module="llama_stack.providers.inline.inference.vllm",
config_class= config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
"llama_stack.providers.inline.inference.vllm.VLLMConfig",
), ),
InlineProviderSpec( InlineProviderSpec(
api=Api.inference, api=Api.inference,
@ -74,8 +74,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="sample", adapter_type="sample",
pip_packages=[], pip_packages=[],
module="llama_stack.providers.remote.inference.sample", module="llama_stack.providers.remote.inference.sample",
config_class= config_class="llama_stack.providers.remote.inference.sample.SampleConfig",
"llama_stack.providers.remote.inference.sample.SampleConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -86,8 +85,7 @@ def available_providers() -> List[ProviderSpec]:
"cerebras_cloud_sdk", "cerebras_cloud_sdk",
], ],
module="llama_stack.providers.remote.inference.cerebras", module="llama_stack.providers.remote.inference.cerebras",
config_class= config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
"llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -95,8 +93,7 @@ def available_providers() -> List[ProviderSpec]:
adapter=AdapterSpec( adapter=AdapterSpec(
adapter_type="ollama", adapter_type="ollama",
pip_packages=["ollama", "aiohttp"], pip_packages=["ollama", "aiohttp"],
config_class= config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
"llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
module="llama_stack.providers.remote.inference.ollama", module="llama_stack.providers.remote.inference.ollama",
), ),
), ),
@ -106,8 +103,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="vllm", adapter_type="vllm",
pip_packages=["openai"], pip_packages=["openai"],
module="llama_stack.providers.remote.inference.vllm", module="llama_stack.providers.remote.inference.vllm",
config_class= config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
"llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -116,8 +112,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="tgi", adapter_type="tgi",
pip_packages=["huggingface_hub", "aiohttp"], pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi", module="llama_stack.providers.remote.inference.tgi",
config_class= config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
"llama_stack.providers.remote.inference.tgi.TGIImplConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -126,8 +121,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="hf::serverless", adapter_type="hf::serverless",
pip_packages=["huggingface_hub", "aiohttp"], pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi", module="llama_stack.providers.remote.inference.tgi",
config_class= config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
"llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -136,8 +130,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="hf::endpoint", adapter_type="hf::endpoint",
pip_packages=["huggingface_hub", "aiohttp"], pip_packages=["huggingface_hub", "aiohttp"],
module="llama_stack.providers.remote.inference.tgi", module="llama_stack.providers.remote.inference.tgi",
config_class= config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
"llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -148,10 +141,8 @@ def available_providers() -> List[ProviderSpec]:
"fireworks-ai", "fireworks-ai",
], ],
module="llama_stack.providers.remote.inference.fireworks", module="llama_stack.providers.remote.inference.fireworks",
config_class= config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
"llama_stack.providers.remote.inference.fireworks.FireworksImplConfig", provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
provider_data_validator=
"llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -162,10 +153,8 @@ def available_providers() -> List[ProviderSpec]:
"together", "together",
], ],
module="llama_stack.providers.remote.inference.together", module="llama_stack.providers.remote.inference.together",
config_class= config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
"llama_stack.providers.remote.inference.together.TogetherImplConfig", provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
provider_data_validator=
"llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -174,8 +163,7 @@ def available_providers() -> List[ProviderSpec]:
adapter_type="bedrock", adapter_type="bedrock",
pip_packages=["boto3"], pip_packages=["boto3"],
module="llama_stack.providers.remote.inference.bedrock", module="llama_stack.providers.remote.inference.bedrock",
config_class= config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
"llama_stack.providers.remote.inference.bedrock.BedrockConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -186,8 +174,7 @@ def available_providers() -> List[ProviderSpec]:
"openai", "openai",
], ],
module="llama_stack.providers.remote.inference.databricks", module="llama_stack.providers.remote.inference.databricks",
config_class= config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
"llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -198,8 +185,7 @@ def available_providers() -> List[ProviderSpec]:
"openai", "openai",
], ],
module="llama_stack.providers.remote.inference.nvidia", module="llama_stack.providers.remote.inference.nvidia",
config_class= config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
"llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -259,8 +245,17 @@ def available_providers() -> List[ProviderSpec]:
"openai", "openai",
], ],
module="llama_stack.providers.remote.inference.sambanova", module="llama_stack.providers.remote.inference.sambanova",
config_class= config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
"llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig", ),
),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="passthrough",
pip_packages=[],
module="llama_stack.providers.remote.inference.passthrough",
config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
), ),
), ),
remote_provider_spec( remote_provider_spec(
@ -277,14 +272,4 @@ def available_providers() -> List[ProviderSpec]:
"llama_stack.providers.remote.inference.centml.CentMLProviderDataValidator", "llama_stack.providers.remote.inference.centml.CentMLProviderDataValidator",
), ),
), ),
remote_provider_spec(
api=Api.inference,
adapter=AdapterSpec(
adapter_type="passthrough",
pip_packages=[],
module="llama_stack.providers.remote.inference.passthrough",
config_class="llama_stack.providers.remote.inference.passthrough.PassthroughImplConfig",
provider_data_validator="llama_stack.providers.remote.inference.passthrough.PassthroughProviderDataValidator",
),
),
] ]