mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-27 18:50:41 +00:00
22dc684da6
# What does this PR do? This PR adds SambaNova as one of the Provider - Add SambaNova as a provider ## Test Plan Test the functional command ``` pytest -s -v --providers inference=sambanova llama_stack/providers/tests/inference/test_embeddings.py llama_stack/providers/tests/inference/test_prompt_adapter.py llama_stack/providers/tests/inference/test_text_inference.py llama_stack/providers/tests/inference/test_vision_inference.py --env SAMBANOVA_API_KEY=<sambanova-api-key> ``` Test the distribution template: ``` # Docker LLAMA_STACK_PORT=5001 docker run -it -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \ llamastack/distribution-sambanova \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY # Conda llama stack build --template sambanova --image-type conda llama stack run ./run.yaml \ --port $LLAMA_STACK_PORT \ --env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY ``` ## Source [SambaNova API Documentation](https://cloud.sambanova.ai/apis) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [Y] Ran pre-commit to handle lint / formatting issues. - [Y] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [Y] Updated relevant documentation. - [Y ] Wrote necessary unit or integration tests. --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
218 lines
8.3 KiB
Python
218 lines
8.3 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
from typing import List
|
|
|
|
from llama_stack.providers.datatypes import (
|
|
AdapterSpec,
|
|
Api,
|
|
InlineProviderSpec,
|
|
ProviderSpec,
|
|
remote_provider_spec,
|
|
)
|
|
|
|
META_REFERENCE_DEPS = [
|
|
"accelerate",
|
|
"blobfile",
|
|
"fairscale",
|
|
"torch",
|
|
"torchvision",
|
|
"transformers",
|
|
"zmq",
|
|
"lm-format-enforcer",
|
|
"sentence-transformers",
|
|
]
|
|
|
|
|
|
def available_providers() -> List[ProviderSpec]:
|
|
return [
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::meta-reference",
|
|
pip_packages=META_REFERENCE_DEPS,
|
|
module="llama_stack.providers.inline.inference.meta_reference",
|
|
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceInferenceConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::meta-reference-quantized",
|
|
pip_packages=(
|
|
META_REFERENCE_DEPS
|
|
+ [
|
|
"fbgemm-gpu",
|
|
"torchao==0.5.0",
|
|
]
|
|
),
|
|
module="llama_stack.providers.inline.inference.meta_reference",
|
|
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::vllm",
|
|
pip_packages=[
|
|
"vllm",
|
|
],
|
|
module="llama_stack.providers.inline.inference.vllm",
|
|
config_class="llama_stack.providers.inline.inference.vllm.VLLMConfig",
|
|
),
|
|
InlineProviderSpec(
|
|
api=Api.inference,
|
|
provider_type="inline::sentence-transformers",
|
|
pip_packages=["sentence-transformers"],
|
|
module="llama_stack.providers.inline.inference.sentence_transformers",
|
|
config_class="llama_stack.providers.inline.inference.sentence_transformers.config.SentenceTransformersInferenceConfig",
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="sample",
|
|
pip_packages=[],
|
|
module="llama_stack.providers.remote.inference.sample",
|
|
config_class="llama_stack.providers.remote.inference.sample.SampleConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="cerebras",
|
|
pip_packages=[
|
|
"cerebras_cloud_sdk",
|
|
],
|
|
module="llama_stack.providers.remote.inference.cerebras",
|
|
config_class="llama_stack.providers.remote.inference.cerebras.CerebrasImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="ollama",
|
|
pip_packages=["ollama", "aiohttp"],
|
|
config_class="llama_stack.providers.remote.inference.ollama.OllamaImplConfig",
|
|
module="llama_stack.providers.remote.inference.ollama",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="vllm",
|
|
pip_packages=["openai"],
|
|
module="llama_stack.providers.remote.inference.vllm",
|
|
config_class="llama_stack.providers.remote.inference.vllm.VLLMInferenceAdapterConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="tgi",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.TGIImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="hf::serverless",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.InferenceAPIImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="hf::endpoint",
|
|
pip_packages=["huggingface_hub", "aiohttp"],
|
|
module="llama_stack.providers.remote.inference.tgi",
|
|
config_class="llama_stack.providers.remote.inference.tgi.InferenceEndpointImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="fireworks",
|
|
pip_packages=[
|
|
"fireworks-ai",
|
|
],
|
|
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",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="together",
|
|
pip_packages=[
|
|
"together",
|
|
],
|
|
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",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="groq",
|
|
pip_packages=["groq"],
|
|
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.GroqProviderDataValidator",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="bedrock",
|
|
pip_packages=["boto3"],
|
|
module="llama_stack.providers.remote.inference.bedrock",
|
|
config_class="llama_stack.providers.remote.inference.bedrock.BedrockConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="databricks",
|
|
pip_packages=[
|
|
"openai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.databricks",
|
|
config_class="llama_stack.providers.remote.inference.databricks.DatabricksImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="nvidia",
|
|
pip_packages=[
|
|
"openai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.nvidia",
|
|
config_class="llama_stack.providers.remote.inference.nvidia.NVIDIAConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="runpod",
|
|
pip_packages=["openai"],
|
|
module="llama_stack.providers.adapters.inference.runpod",
|
|
config_class="llama_stack.providers.adapters.inference.runpod.RunpodImplConfig",
|
|
),
|
|
),
|
|
remote_provider_spec(
|
|
api=Api.inference,
|
|
adapter=AdapterSpec(
|
|
adapter_type="sambanova",
|
|
pip_packages=[
|
|
"openai",
|
|
],
|
|
module="llama_stack.providers.remote.inference.sambanova",
|
|
config_class="llama_stack.providers.remote.inference.sambanova.SambaNovaImplConfig",
|
|
),
|
|
),
|
|
]
|