mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-27 13:08:03 +00:00
chore: Enabling Milvus for VectorIO CI
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
This commit is contained in:
Francisco Javier Arceo
parent
709eb7da33
commit
c8d41d45ec
115 changed files with 2919 additions and 184 deletions
|
|
@ -35,6 +35,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=META_REFERENCE_DEPS,
|
||||
module="llama_stack.providers.inline.inference.meta_reference",
|
||||
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
|
||||
description="Meta's reference implementation of inference with support for various model formats and optimization techniques.",
|
||||
),
|
||||
InlineProviderSpec(
|
||||
api=Api.inference,
|
||||
|
|
@ -44,6 +45,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
],
|
||||
module="llama_stack.providers.inline.inference.vllm",
|
||||
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
|
||||
description="vLLM inference provider for high-performance model serving with PagedAttention and continuous batching.",
|
||||
),
|
||||
InlineProviderSpec(
|
||||
api=Api.inference,
|
||||
|
|
@ -54,6 +56,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
],
|
||||
module="llama_stack.providers.inline.inference.sentence_transformers",
|
||||
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
|
||||
description="Sentence Transformers inference provider for text embeddings and similarity search.",
|
||||
),
|
||||
remote_provider_spec(
|
||||
api=Api.inference,
|
||||
|
|
@ -64,6 +67,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
],
|
||||
module="llama_stack.providers.remote.inference.cerebras",
|
||||
config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
|
||||
description="Cerebras inference provider for running models on Cerebras Cloud platform.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -73,6 +77,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["ollama", "aiohttp", "h11>=0.16.0"],
|
||||
config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
|
||||
module="llama_stack.providers.remote.inference.ollama",
|
||||
description="Ollama inference provider for running local models through the Ollama runtime.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -82,6 +87,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["openai"],
|
||||
module="llama_stack.providers.remote.inference.vllm",
|
||||
config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
|
||||
description="Remote vLLM inference provider for connecting to vLLM servers.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -91,6 +97,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["huggingface_hub", "aiohttp"],
|
||||
module="llama_stack.providers.remote.inference.tgi",
|
||||
config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
|
||||
description="Text Generation Inference (TGI) provider for HuggingFace model serving.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -100,6 +107,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["huggingface_hub", "aiohttp"],
|
||||
module="llama_stack.providers.remote.inference.tgi",
|
||||
config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
|
||||
description="HuggingFace Inference API serverless provider for on-demand model inference.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -109,6 +117,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["huggingface_hub", "aiohttp"],
|
||||
module="llama_stack.providers.remote.inference.tgi",
|
||||
config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
|
||||
description="HuggingFace Inference Endpoints provider for dedicated model serving.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -121,6 +130,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.fireworks",
|
||||
config_class="llama_stack.providers.remote.inference.fireworks.FireworksImplConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.fireworks.FireworksProviderDataValidator",
|
||||
description="Fireworks AI inference provider for Llama models and other AI models on the Fireworks platform.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -133,6 +143,7 @@ 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.inference.together.TogetherProviderDataValidator",
|
||||
description="Together AI inference provider for open-source models and collaborative AI development.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -142,6 +153,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["boto3"],
|
||||
module="llama_stack.providers.remote.inference.bedrock",
|
||||
config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
|
||||
description="AWS Bedrock inference provider for accessing various AI models through AWS's managed service.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -153,6 +165,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
],
|
||||
module="llama_stack.providers.remote.inference.databricks",
|
||||
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
|
||||
description="Databricks inference provider for running models on Databricks' unified analytics platform.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -164,6 +177,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
],
|
||||
module="llama_stack.providers.remote.inference.nvidia",
|
||||
config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
|
||||
description="NVIDIA inference provider for accessing NVIDIA NIM models and AI services.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -173,6 +187,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
pip_packages=["openai"],
|
||||
module="llama_stack.providers.remote.inference.runpod",
|
||||
config_class="llama_stack.providers.remote.inference.runpod.RunpodImplConfig",
|
||||
description="RunPod inference provider for running models on RunPod's cloud GPU platform.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -183,6 +198,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.openai",
|
||||
config_class="llama_stack.providers.remote.inference.openai.OpenAIConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.openai.config.OpenAIProviderDataValidator",
|
||||
description="OpenAI inference provider for accessing GPT models and other OpenAI services.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -193,6 +209,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.anthropic",
|
||||
config_class="llama_stack.providers.remote.inference.anthropic.AnthropicConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.anthropic.config.AnthropicProviderDataValidator",
|
||||
description="Anthropic inference provider for accessing Claude models and Anthropic's AI services.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -203,6 +220,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.gemini",
|
||||
config_class="llama_stack.providers.remote.inference.gemini.GeminiConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.gemini.config.GeminiProviderDataValidator",
|
||||
description="Google Gemini inference provider for accessing Gemini models and Google's AI services.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -213,6 +231,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.groq",
|
||||
config_class="llama_stack.providers.remote.inference.groq.GroqConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.groq.config.GroqProviderDataValidator",
|
||||
description="Groq inference provider for ultra-fast inference using Groq's LPU technology.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -223,6 +242,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.fireworks_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.fireworks_openai_compat.config.FireworksProviderDataValidator",
|
||||
description="Fireworks AI OpenAI-compatible provider for using Fireworks models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -233,6 +253,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.llama_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.llama_openai_compat.config.LlamaProviderDataValidator",
|
||||
description="Llama OpenAI-compatible provider for using Llama models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -243,6 +264,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.together_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.together_openai_compat.config.TogetherProviderDataValidator",
|
||||
description="Together AI OpenAI-compatible provider for using Together models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -253,6 +275,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.groq_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.groq_openai_compat.config.GroqProviderDataValidator",
|
||||
description="Groq OpenAI-compatible provider for using Groq models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -263,6 +286,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.sambanova_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.sambanova_openai_compat.config.SambaNovaProviderDataValidator",
|
||||
description="SambaNova OpenAI-compatible provider for using SambaNova models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -273,6 +297,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.cerebras_openai_compat",
|
||||
config_class="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasCompatConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.cerebras_openai_compat.config.CerebrasProviderDataValidator",
|
||||
description="Cerebras OpenAI-compatible provider for using Cerebras models with OpenAI API format.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -283,6 +308,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.sambanova",
|
||||
config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.sambanova.config.SambaNovaProviderDataValidator",
|
||||
description="SambaNova inference provider for running models on SambaNova's dataflow architecture.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -293,6 +319,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
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",
|
||||
description="Passthrough inference provider for connecting to any external inference service not directly supported.",
|
||||
),
|
||||
),
|
||||
remote_provider_spec(
|
||||
|
|
@ -303,6 +330,7 @@ def available_providers() -> list[ProviderSpec]:
|
|||
module="llama_stack.providers.remote.inference.watsonx",
|
||||
config_class="llama_stack.providers.remote.inference.watsonx.WatsonXConfig",
|
||||
provider_data_validator="llama_stack.providers.remote.inference.watsonx.WatsonXProviderDataValidator",
|
||||
description="IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform.",
|
||||
),
|
||||
),
|
||||
]
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue