phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-18 07:18:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add provider deprecation support; change directory structure

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-07 12:34:23 -08:00
parent 36e2538eb0
commit 0747ee2f10
50 changed files with 56 additions and 41 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/registry/agents.py
View file

@ -22,8 +22,8 @@ def available_providers() -> List[ProviderSpec]:
"scikit-learn",
]
+ kvstore_dependencies(),
module="llama_stack.providers.inline.meta_reference.agents",
config_class="llama_stack.providers.inline.meta_reference.agents.MetaReferenceAgentsImplConfig",
module="llama_stack.providers.inline.agents.meta_reference",
config_class="llama_stack.providers.inline.agents.meta_reference.MetaReferenceAgentsImplConfig",
api_dependencies=[
Api.inference,
Api.safety,

26
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,
@ -140,13 +149,4 @@ def available_providers() -> List[ProviderSpec]:
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
),
),
InlineProviderSpec(
api=Api.inference,
provider_type="vllm",
pip_packages=[
"vllm",
],
module="llama_stack.providers.inline.vllm",
config_class="llama_stack.providers.inline.vllm.VLLMConfig",
),
]

12
llama_stack/providers/registry/memory.py
View file

@ -36,8 +36,16 @@ def available_providers() -> List[ProviderSpec]:
api=Api.memory,
provider_type="meta-reference",
pip_packages=EMBEDDING_DEPS + ["faiss-cpu"],
module="llama_stack.providers.inline.meta_reference.memory",
config_class="llama_stack.providers.inline.meta_reference.memory.FaissImplConfig",
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
deprecation_warning="Please use the `faiss` provider instead.",
),
InlineProviderSpec(
api=Api.memory,
provider_type="faiss",
pip_packages=EMBEDDING_DEPS + ["faiss-cpu"],
module="llama_stack.providers.inline.memory.faiss",
config_class="llama_stack.providers.inline.memory.faiss.FaissImplConfig",
),
remote_provider_spec(
Api.memory,