phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 19:19:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Add SambaNova Providier

Browse source
This commit is contained in:
Edward Ma 2024-12-02 08:09:55 -08:00
parent fe48b9fb8c
commit d7b159663c
17 changed files with 733 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
docs/source/concepts/index.md
View file

@ -25,7 +25,7 @@ We are working on adding a few more APIs to complete the application lifecycle.
## API Providers
The goal of Llama Stack is to build an ecosystem where users can easily swap out different implementations for the same API. Obvious examples for these include
- LLM inference providers (e.g., Fireworks, Together, AWS Bedrock, etc.),
- LLM inference providers (e.g., Fireworks, Together, AWS Bedrock, SambaNova, etc.),
- Vector databases (e.g., ChromaDB, Weaviate, Qdrant, etc.),
- Safety providers (e.g., Meta's Llama Guard, AWS Bedrock Guardrails, etc.)

8
docs/source/distributions/building_distro.md
View file

@ -109,6 +109,14 @@ llama stack build --list-templates
| | "telemetry": "meta-reference" | |
| | } | |
+------------------------------+--------------------------------------------+----------------------------------------------------------------------------------+
| sambanova | { | Use SambaNova.ai for running LLM inference |
| | "inference": "remote::sambanova", | |
| | "memory": "meta-reference", | |
| | "safety": "meta-reference", | |
| | "agents": "meta-reference", | |
| | "telemetry": "meta-reference" | |
| | } | |
+------------------------------+--------------------------------------------+----------------------------------------------------------------------------------+
| vllm | { | Like local, but use vLLM for running LLM inference |
| | "inference": "vllm", | |
| | "memory": "meta-reference", | |

74
docs/source/distributions/self_hosted_distro/sambanova.md Normal file
View file

@ -0,0 +1,74 @@
---
orphan: true
---
# SambaNova Distribution
```{toctree}
:maxdepth: 2
:hidden:
self
```
The `llamastack/distribution-sambanova` distribution consists of the following provider configurations.
| API | Provider(s) |
|-----|-------------|
| agents | `inline::meta-reference` |
| inference | `remote::sambanova` |
| memory | `inline::faiss`, `remote::chromadb`, `remote::pgvector` |
| safety | `inline::llama-guard` |
| telemetry | `inline::meta-reference` |
### Environment Variables
The following environment variables can be configured:
- `LLAMASTACK_PORT`: Port for the Llama Stack distribution server (default: `5001`)
- `SAMBANOVA_API_KEY`: SambaNova.AI API Key (default: ``)
### Models
The following models are available by default:
- `meta-llama/Llama-3.1-8B-Instruct`
- `meta-llama/Llama-3.1-70B-Instruct`
- `meta-llama/Llama-3.1-405B-Instruct`
- `meta-llama/Llama-3.2-1B-Instruct`
- `meta-llama/Llama-3.2-3B-Instruct`
- `meta-llama/Llama-3.2-11B-Vision-Instruct`
- `meta-llama/Llama-3.2-90B-Vision-Instruct`
### Prerequisite: API Keys
Make sure you have access to a SambaNova API Key. You can get one by visiting [SambaBova.ai](https://sambanova.ai/).
## Running Llama Stack with SambaNova
You can do this via Conda (build code) or Docker which has a pre-built image.
### Via Docker
This method allows you to get started quickly without having to build the distribution code.
```bash
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
```
### Via Conda
```bash
llama stack build --template sambanova --image-type conda
llama stack run ./run.yaml \
--port $LLAMA_STACK_PORT \
--env SAMBANOVA_API_KEY=$SAMBANOVA_API_KEY
```

1
docs/source/index.md
View file

@ -48,6 +48,7 @@ Llama Stack already has a number of "adapters" available for some popular Infere
| Fireworks | Hosted | Y | Y | Y | | |
| AWS Bedrock | Hosted | | Y | | Y | |
| Together | Hosted | Y | Y | | Y | |
| SambaNova | Hosted | | Y | | | |
| Ollama | Single Node | | Y | | |
| TGI | Hosted and Single Node | | Y | | |
| Chroma | Single Node | | | Y | | |