phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/README.md
Henry Tu 64c6df8392
Cerebras Inference Integration (#265) 
Adding Cerebras Inference as an API provider.

## Testing

### Conda
```
$ llama stack build --template cerebras --image-type conda
$ llama stack run ~/.llama/distributions/llamastack-cerebras/cerebras-run.yaml
...
Listening on ['::', '0.0.0.0']:5000
INFO:     Started server process [12443]
INFO:     Waiting for application startup.
INFO:     Application startup complete.
INFO:     Uvicorn running on http://['::', '0.0.0.0']:5000 (Press CTRL+C to quit)
```

### Chat Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/chat-completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "messages": [
        {
            "role": "user",
            "content": "What is the temperature in Seattle right now?"
        }
    ],
    "stream": false,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 100
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}' 
```

#### Non-Streaming Response
```
{
  "completion_message": {
    "role": "assistant",
    "content": "",
    "stop_reason": "end_of_message",
    "tool_calls": [
      {
        "call_id": "6f42fdcc-6cbb-46ad-a17b-5d20ac64b678",
        "tool_name": "getTemperature",
        "arguments": {
          "location": "Seattle"
        }
      }
    ]
  },
  "logprobs": null
}
```

#### Streaming Response
```
data: {"event":{"event_type":"start","delta":"","logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"","parse_status":"started"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"{\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"type","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"function","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"name","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"get","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Temperature","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\",","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"parameters","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" {\"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"location","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\":","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":" \"","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"Seattle","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":"\"}}","parse_status":"in_progress"},"logprobs":null,"stop_reason":null}}
data: {"event":{"event_type":"progress","delta":{"content":{"call_id":"e742df1f-0ae9-40ad-a49e-18e5c905484f","tool_name":"getTemperature","arguments":{"location":"Seattle"}},"parse_status":"success"},"logprobs":null,"stop_reason":"end_of_message"}}
data: {"event":{"event_type":"complete","delta":"","logprobs":null,"stop_reason":"end_of_message"}}
```

### Completion
```
$ curl --location 'http://localhost:5000/alpha/inference/completion' --header 'Content-Type: application/json' --data '{
    "model_id": "meta-llama/Llama-3.1-8B-Instruct",
    "content": "1,2,3,",
    "stream": true,
    "sampling_params": {
        "strategy": "top_p",
        "temperature": 0.5,
        "max_tokens": 10
    },                   
    "tool_choice": "auto",
    "tool_prompt_format": "json",
    "tools": [                   
        {
            "tool_name": "getTemperature",
            "description": "Gets the current temperature of a location.",
            "parameters": {                                              
                "location": {
                    "param_type": "string",
                    "description": "The name of the place to get the temperature from in degress celsius.",
                    "required": true                                                                       
                }                   
            }    
        }    
    ]    
}'
```

#### Non-Streaming Response
```
{
  "content": "4,5,6,7,8,",
  "stop_reason": "out_of_tokens",
  "logprobs": null
}
```

#### Streaming Response
```
data: {"delta":"4","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"5","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"6","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"7","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"8","stop_reason":null,"logprobs":null}
data: {"delta":",","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":null,"logprobs":null}
data: {"delta":"","stop_reason":"out_of_tokens","logprobs":null}
```

### Pre-Commit Checks
```
trim trailing whitespace.................................................Passed
check python ast.........................................................Passed
check for merge conflicts................................................Passed
check for added large files..............................................Passed
fix end of files.........................................................Passed
Insert license in comments...............................................Passed
flake8...................................................................Passed
Format files with µfmt...................................................Passed
```

### Testing with `test_inference.py`
```
$ export CEREBRAS_API_KEY=<insert API key here>
$ pytest -v -s llama_stack/providers/tests/inference/test_text_inference.py -m "cerebras and llama_8b" 
/net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/lib/python3.12/site-packages/pytest_asyncio/plugin.py:208: PytestDeprecationWarning: The configuration option "asyncio_default_fixture_loop_scope" is unset.
The event loop scope for asynchronous fixtures will default to the fixture caching scope. Future versions of pytest-asyncio will default the loop scope for asynchronous fixtures to function scope. Set the default fixture loop scope explicitly in order to avoid unexpected behavior in the future. Valid fixture loop scopes are: "function", "class", "module", "package", "session"

  warnings.warn(PytestDeprecationWarning(_DEFAULT_FIXTURE_LOOP_SCOPE_UNSET))
=================================================== test session starts ===================================================
platform linux -- Python 3.12.3, pytest-8.3.3, pluggy-1.5.0 -- /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack/.venv/bin/python3.12
cachedir: .pytest_cache
rootdir: /net/henryt-dev/srv/nfs/henryt-data/ws/llama-stack
configfile: pyproject.toml
plugins: anyio-4.6.2.post1, asyncio-0.24.0
asyncio: mode=Mode.STRICT, default_loop_scope=None
collected 128 items / 120 deselected / 8 selected                                                                         

llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_model_list[llama_8b-cerebras] Resolved 4 providers
 inner-inference => cerebras
 models => __routing_table__
 inference => __autorouted__
 inspect => __builtin__

Models: meta-llama/Llama-3.1-8B-Instruct served by cerebras

PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completion[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_completions_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_non_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_structured_output[llama_8b-cerebras] SKIPPED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_streaming[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling[llama_8b-cerebras] PASSED
llama_stack/providers/tests/inference/test_text_inference.py::TestInference::test_chat_completion_with_tool_calling_streaming[llama_8b-cerebras] PASSED

================================ 6 passed, 2 skipped, 120 deselected, 6 warnings in 3.95s =================================
```

I ran `python llama_stack/scripts/distro_codegen.py` to run codegen.
2024-12-03 21:15:32 -08:00

11 KiB
Raw Blame History

Llama Stack

PyPI version PyPI - Downloads Discord

Quick Start | Documentation | Zero-to-Hero Guide

Llama Stack defines and standardizes the set of core building blocks needed to bring generative AI applications to market. These building blocks are presented in the form of interoperable APIs with a broad set of Service Providers providing their implementations.

Llama Stack

Our goal is to provide pre-packaged implementations which can be operated in a variety of deployment environments: developers start iterating with Desktops or their mobile devices and can seamlessly transition to on-prem or public cloud deployments. At every point in this transition, the same set of APIs and the same developer experience is available.

⚠️ Note The Stack APIs are rapidly improving, but still very much work in progress and we invite feedback as well as direct contributions.

APIs

We have working implementations of the following APIs today:

  • Inference
  • Safety
  • Memory
  • Agents
  • Eval
  • Telemetry

Alongside these APIs, we also related APIs for operating with associated resources (see Concepts):

  • Models
  • Shields
  • Memory Banks
  • EvalTasks
  • Datasets
  • Scoring Functions

We are also working on the following APIs which will be released soon:

  • Post Training
  • Synthetic Data Generation
  • Reward Scoring

Each of the APIs themselves is a collection of REST endpoints.

Philosophy

Service-oriented design

Unlike other frameworks, Llama Stack is built with a service-oriented, REST API-first approach. Such a design not only allows for seamless transitions from a local to remote deployments, but also forces the design to be more declarative. We believe this restriction can result in a much simpler, robust developer experience. This will necessarily trade-off against expressivity however if we get the APIs right, it can lead to a very powerful platform.

Composability

We expect the set of APIs we design to be composable. An Agent abstractly depends on { Inference, Memory, Safety } APIs but does not care about the actual implementation details. Safety itself may require model inference and hence can depend on the Inference API.

Turnkey one-stop solutions

We expect to provide turnkey solutions for popular deployment scenarios. It should be easy to deploy a Llama Stack server on AWS or on a private data center. Either of these should allow a developer to get started with powerful agentic apps, model evaluations or fine-tuning services in a matter of minutes. They should all result in the same uniform observability and developer experience.

Focus on Llama models

As a Meta initiated project, we have started by explicitly focusing on Meta's Llama series of models. Supporting the broad set of open models is no easy task and we want to start with models we understand best.

Supporting the Ecosystem

There is a vibrant ecosystem of Providers which provide efficient inference or scalable vector stores or powerful observability solutions. We want to make sure it is easy for developers to pick and choose the best implementations for their use cases. We also want to make sure it is easy for new Providers to onboard and participate in the ecosystem.

Additionally, we have designed every element of the Stack such that APIs as well as Resources (like Models) can be federated.

Supported Llama Stack Implementations

API Providers

API Provider Builder Environments Agents Inference Memory Safety Telemetry
Meta Reference Single Node ✔️ ✔️ ✔️ ✔️ ✔️
Cerebras Single Node ✔️
Fireworks Hosted ✔️ ✔️ ✔️
AWS Bedrock Hosted ✔️ ✔️
Together Hosted ✔️ ✔️ ✔️
Ollama Single Node ✔️
TGI Hosted and Single Node ✔️
Chroma Single Node ✔️
PG Vector Single Node ✔️
PyTorch ExecuTorch On-device iOS ✔️ ✔️

Distributions

Distribution Llama Stack Docker Start This Distribution
Meta Reference llamastack/distribution-meta-reference-gpu Guide
Meta Reference Quantized llamastack/distribution-meta-reference-quantized-gpu Guide
Cerebras llamastack/distribution-cerebras Guide
Ollama llamastack/distribution-ollama Guide
TGI llamastack/distribution-tgi Guide
Together llamastack/distribution-together Guide
Fireworks llamastack/distribution-fireworks Guide

Installation

You have two ways to install this repository:

  1. Install as a package: You can install the repository directly from PyPI by running the following command:

    pip install llama-stack

  2. Install from source: If you prefer to install from the source code, follow these steps:

     mkdir -p ~/local
 cd ~/local
 git clone git@github.com:meta-llama/llama-stack.git

 conda create -n stack python=3.10
 conda activate stack

 cd llama-stack
 $CONDA_PREFIX/bin/pip install -e .

Documentation

Please checkout our Documentation page for more details.

Llama Stack Client SDKs

Language Client SDK Package
Python llama-stack-client-python PyPI version
Swift llama-stack-client-swift Swift Package Index
Node llama-stack-client-node NPM version
Kotlin llama-stack-client-kotlin Maven version

Check out our client SDKs for connecting to Llama Stack server in your preferred language, you can choose from python, node, swift, and kotlin programming languages to quickly build your applications.

You can find more example scripts with client SDKs to talk with the Llama Stack server in our llama-stack-apps repo.