phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-16 06:53:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' of https://github.com/santiagxf/llama-stack into santiagxf/azure-ai-inference

Browse source
This commit is contained in:
Facundo Santiago 2024-11-08 15:04:48 +00:00
commit 75f742775d
98 changed files with 1131 additions and 586 deletions
Download patch file Download diff file Expand all files Collapse all files

28
llama_stack/providers/registry/inference.py
View file

@ -27,8 +27,8 @@ def available_providers() -> List[ProviderSpec]:
api=Api.inference,
provider_type="meta-reference",
pip_packages=META_REFERENCE_DEPS,
module="llama_stack.providers.inline.meta_reference.inference",
config_class="llama_stack.providers.inline.meta_reference.inference.MetaReferenceInferenceConfig",
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
),
InlineProviderSpec(
api=Api.inference,
@ -40,8 +40,17 @@ def available_providers() -> List[ProviderSpec]:
"torchao==0.5.0",
]
),
module="llama_stack.providers.inline.meta_reference.inference",
config_class="llama_stack.providers.inline.meta_reference.inference.MetaReferenceQuantizedInferenceConfig",
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="vllm",
pip_packages=[
"vllm",
],
module="llama_stack.providers.inline.inference.vllm",
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
),
remote_provider_spec(
api=Api.inference,
@ -117,7 +126,7 @@ def available_providers() -> List[ProviderSpec]:
],
module="llama_stack.providers.remote.inference.together",
config_class="llama_stack.providers.remote.inference.together.TogetherImplConfig",
provider_data_validator="llama_stack.providers.remote.safety.together.TogetherProviderDataValidator",
provider_data_validator="llama_stack.providers.remote.inference.together.TogetherProviderDataValidator",
),
),
remote_provider_spec(
@ -149,13 +158,4 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.adapters.inference.azure_ai_inference.AzureAIInferenceConfig",
),
),
InlineProviderSpec(
api=Api.inference,
provider_type="vllm",
pip_packages=[
"vllm",
],
module="llama_stack.providers.inline.vllm",
config_class="llama_stack.providers.inline.vllm.VLLMConfig",
),
]