phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-28 17:42:00 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'meta-llama:main' into feat/litellm_sambanova_usage

Browse source
This commit is contained in:
Jorge Piedrahita Ortiz 2025-04-14 08:51:59 -05:00 • committed by GitHub
commit dd808a8c1e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
57 changed files with 1392 additions and 671 deletions
Download patch file Download diff file Expand all files Collapse all files

188
docs/_static/llama-stack-spec.html vendored
View file

@ -85,7 +85,7 @@
}
}
},
"/v1/batch-inference/chat-completion": {
"/v1/inference/batch-chat-completion": {
"post": {
"responses": {
"200": {
@ -112,7 +112,7 @@
}
},
"tags": [
"BatchInference (Coming Soon)"
"Inference"
],
"description": "",
"parameters": [],
@ -128,7 +128,7 @@
}
}
},
"/v1/batch-inference/completion": {
"/v1/inference/batch-completion": {
"post": {
"responses": {
"200": {
@ -155,7 +155,7 @@
}
},
"tags": [
"BatchInference (Coming Soon)"
"Inference"
],
"description": "",
"parameters": [],
@ -239,7 +239,7 @@
}
},
"tags": [
"Inference"
"BatchInference (Coming Soon)"
],
"description": "Generate a chat completion for the given messages using the specified model.",
"parameters": [],
@ -287,7 +287,7 @@
}
},
"tags": [
"Inference"
"BatchInference (Coming Soon)"
],
"description": "Generate a completion for the given content using the specified model.",
"parameters": [],
@ -4366,6 +4366,51 @@
],
"title": "ToolCall"
},
"ToolConfig": {
"type": "object",
"properties": {
"tool_choice": {
"oneOf": [
{
"type": "string",
"enum": [
"auto",
"required",
"none"
],
"title": "ToolChoice",
"description": "Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."
},
{
"type": "string"
}
],
"default": "auto",
"description": "(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."
},
"tool_prompt_format": {
"type": "string",
"enum": [
"json",
"function_tag",
"python_list"
],
"description": "(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name> tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."
},
"system_message_behavior": {
"type": "string",
"enum": [
"append",
"replace"
],
"description": "(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.",
"default": "append"
}
},
"additionalProperties": false,
"title": "ToolConfig",
"description": "Configuration for tool use."
},
"ToolDefinition": {
"type": "object",
"properties": {
@ -4554,7 +4599,7 @@
"BatchChatCompletionRequest": {
"type": "object",
"properties": {
"model": {
"model_id": {
"type": "string"
},
"messages_batch": {
@ -4575,25 +4620,8 @@
"$ref": "#/components/schemas/ToolDefinition"
}
},
"tool_choice": {
"type": "string",
"enum": [
"auto",
"required",
"none"
],
"title": "ToolChoice",
"description": "Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."
},
"tool_prompt_format": {
"type": "string",
"enum": [
"json",
"function_tag",
"python_list"
],
"title": "ToolPromptFormat",
"description": "Prompt format for calling custom / zero shot tools."
"tool_config": {
"$ref": "#/components/schemas/ToolConfig"
},
"response_format": {
"$ref": "#/components/schemas/ResponseFormat"
@ -4613,7 +4641,7 @@
},
"additionalProperties": false,
"required": [
"model",
"model_id",
"messages_batch"
],
"title": "BatchChatCompletionRequest"
@ -4710,7 +4738,7 @@
"BatchCompletionRequest": {
"type": "object",
"properties": {
"model": {
"model_id": {
"type": "string"
},
"content_batch": {
@ -4740,7 +4768,7 @@
},
"additionalProperties": false,
"required": [
"model",
"model_id",
"content_batch"
],
"title": "BatchCompletionRequest"
@ -4812,51 +4840,6 @@
],
"title": "CancelTrainingJobRequest"
},
"ToolConfig": {
"type": "object",
"properties": {
"tool_choice": {
"oneOf": [
{
"type": "string",
"enum": [
"auto",
"required",
"none"
],
"title": "ToolChoice",
"description": "Whether tool use is required or automatic. This is a hint to the model which may not be followed. It depends on the Instruction Following capabilities of the model."
},
{
"type": "string"
}
],
"default": "auto",
"description": "(Optional) Whether tool use is automatic, required, or none. Can also specify a tool name to use a specific tool. Defaults to ToolChoice.auto."
},
"tool_prompt_format": {
"type": "string",
"enum": [
"json",
"function_tag",
"python_list"
],
"description": "(Optional) Instructs the model how to format tool calls. By default, Llama Stack will attempt to use a format that is best adapted to the model. - `ToolPromptFormat.json`: The tool calls are formatted as a JSON object. - `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name> tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python syntax -- a list of function calls."
},
"system_message_behavior": {
"type": "string",
"enum": [
"append",
"replace"
],
"description": "(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`: Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`: Replaces the default system prompt with the provided system message. The system message can include the string '{{function_definitions}}' to indicate where the function definitions should be inserted.",
"default": "append"
}
},
"additionalProperties": false,
"title": "ToolConfig",
"description": "Configuration for tool use."
},
"ChatCompletionRequest": {
"type": "object",
"properties": {
@ -7906,7 +7889,13 @@
"type": "object",
"properties": {
"status": {
"type": "string"
"type": "string",
"enum": [
"OK",
"Error",
"Not Implemented"
],
"title": "HealthStatus"
}
},
"additionalProperties": false,
@ -8101,6 +8090,31 @@
}
]
}
},
"health": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
@ -8108,7 +8122,8 @@
"api",
"provider_id",
"provider_type",
"config"
"config",
"health"
],
"title": "ProviderInfo"
},
@ -9778,13 +9793,16 @@
"type": "integer"
},
"max_steps_per_epoch": {
"type": "integer"
"type": "integer",
"default": 1
},
"gradient_accumulation_steps": {
"type": "integer"
"type": "integer",
"default": 1
},
"max_validation_steps": {
"type": "integer"
"type": "integer",
"default": 1
},
"data_config": {
"$ref": "#/components/schemas/DataConfig"
@ -9804,10 +9822,7 @@
"required": [
"n_epochs",
"max_steps_per_epoch",
"gradient_accumulation_steps",
"max_validation_steps",
"data_config",
"optimizer_config"
"gradient_accumulation_steps"
],
"title": "TrainingConfig"
},
@ -10983,8 +10998,7 @@
"job_uuid",
"training_config",
"hyperparam_search_config",
"logger_config",
"model"
"logger_config"
],
"title": "SupervisedFineTuneRequest"
},
@ -11174,7 +11188,9 @@
"x-displayName": "Agents API for creating and interacting with agentic systems."
},
{
"name": "BatchInference (Coming Soon)"
"name": "BatchInference (Coming Soon)",
"description": "This is an asynchronous API. If the request is successful, the response will be a job which can be polled for completion.\n\nNOTE: This API is not yet implemented and is subject to change in concert with other asynchronous APIs\nincluding (post-training, evals, etc).",
"x-displayName": "Batch inference API for generating completions and chat completions."
},
{
"name": "Benchmarks"

172
docs/_static/llama-stack-spec.yaml vendored
View file

@ -40,7 +40,7 @@ paths:
schema:
$ref: '#/components/schemas/AppendRowsRequest'
required: true
/v1/batch-inference/chat-completion:
/v1/inference/batch-chat-completion:
post:
responses:
'200':
@ -60,7 +60,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
- Inference
description: ''
parameters: []
requestBody:
@ -69,7 +69,7 @@ paths:
schema:
$ref: '#/components/schemas/BatchChatCompletionRequest'
required: true
/v1/batch-inference/completion:
/v1/inference/batch-completion:
post:
responses:
'200':
@ -89,7 +89,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- BatchInference (Coming Soon)
- Inference
description: ''
parameters: []
requestBody:
@ -148,7 +148,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
- BatchInference (Coming Soon)
description: >-
Generate a chat completion for the given messages using the specified model.
parameters: []
@ -183,7 +183,7 @@ paths:
default:
$ref: '#/components/responses/DefaultError'
tags:
- Inference
- BatchInference (Coming Soon)
description: >-
Generate a completion for the given content using the specified model.
parameters: []
@ -3009,6 +3009,54 @@ components:
- tool_name
- arguments
title: ToolCall
ToolConfig:
type: object
properties:
tool_choice:
oneOf:
- type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following
capabilities of the model.
- type: string
default: auto
description: >-
(Optional) Whether tool use is automatic, required, or none. Can also
specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls.
system_message_behavior:
type: string
enum:
- append
- replace
description: >-
(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`:
Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`:
Replaces the default system prompt with the provided system message. The
system message can include the string '{{function_definitions}}' to indicate
where the function definitions should be inserted.
default: append
additionalProperties: false
title: ToolConfig
description: Configuration for tool use.
ToolDefinition:
type: object
properties:
@ -3145,7 +3193,7 @@ components:
BatchChatCompletionRequest:
type: object
properties:
model:
model_id:
type: string
messages_batch:
type: array
@ -3159,26 +3207,8 @@ components:
type: array
items:
$ref: '#/components/schemas/ToolDefinition'
tool_choice:
type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following capabilities
of the model.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
title: ToolPromptFormat
description: >-
Prompt format for calling custom / zero shot tools.
tool_config:
$ref: '#/components/schemas/ToolConfig'
response_format:
$ref: '#/components/schemas/ResponseFormat'
logprobs:
@ -3193,7 +3223,7 @@ components:
title: LogProbConfig
additionalProperties: false
required:
- model
- model_id
- messages_batch
title: BatchChatCompletionRequest
BatchChatCompletionResponse:
@ -3261,7 +3291,7 @@ components:
BatchCompletionRequest:
type: object
properties:
model:
model_id:
type: string
content_batch:
type: array
@ -3283,7 +3313,7 @@ components:
title: LogProbConfig
additionalProperties: false
required:
- model
- model_id
- content_batch
title: BatchCompletionRequest
BatchCompletionResponse:
@ -3335,54 +3365,6 @@ components:
required:
- job_uuid
title: CancelTrainingJobRequest
ToolConfig:
type: object
properties:
tool_choice:
oneOf:
- type: string
enum:
- auto
- required
- none
title: ToolChoice
description: >-
Whether tool use is required or automatic. This is a hint to the model
which may not be followed. It depends on the Instruction Following
capabilities of the model.
- type: string
default: auto
description: >-
(Optional) Whether tool use is automatic, required, or none. Can also
specify a tool name to use a specific tool. Defaults to ToolChoice.auto.
tool_prompt_format:
type: string
enum:
- json
- function_tag
- python_list
description: >-
(Optional) Instructs the model how to format tool calls. By default, Llama
Stack will attempt to use a format that is best adapted to the model.
- `ToolPromptFormat.json`: The tool calls are formatted as a JSON object.
- `ToolPromptFormat.function_tag`: The tool calls are enclosed in a <function=function_name>
tag. - `ToolPromptFormat.python_list`: The tool calls are output as Python
syntax -- a list of function calls.
system_message_behavior:
type: string
enum:
- append
- replace
description: >-
(Optional) Config for how to override the default system prompt. - `SystemMessageBehavior.append`:
Appends the provided system message to the default system prompt. - `SystemMessageBehavior.replace`:
Replaces the default system prompt with the provided system message. The
system message can include the string '{{function_definitions}}' to indicate
where the function definitions should be inserted.
default: append
additionalProperties: false
title: ToolConfig
description: Configuration for tool use.
ChatCompletionRequest:
type: object
properties:
@ -5481,6 +5463,11 @@ components:
properties:
status:
type: string
enum:
- OK
- Error
- Not Implemented
title: HealthStatus
additionalProperties: false
required:
- status
@ -5592,12 +5579,23 @@ components:
- type: string
- type: array
- type: object
health:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- api
- provider_id
- provider_type
- config
- health
title: ProviderInfo
InvokeToolRequest:
type: object
@ -6744,10 +6742,13 @@ components:
type: integer
max_steps_per_epoch:
type: integer
default: 1
gradient_accumulation_steps:
type: integer
default: 1
max_validation_steps:
type: integer
default: 1
data_config:
$ref: '#/components/schemas/DataConfig'
optimizer_config:
@ -6762,9 +6763,6 @@ components:
- n_epochs
- max_steps_per_epoch
- gradient_accumulation_steps
- max_validation_steps
- data_config
- optimizer_config
title: TrainingConfig
PreferenceOptimizeRequest:
type: object
@ -7498,7 +7496,6 @@ components:
- training_config
- hyperparam_search_config
- logger_config
- model
title: SupervisedFineTuneRequest
SyntheticDataGenerateRequest:
type: object
@ -7633,6 +7630,17 @@ tags:
x-displayName: >-
Agents API for creating and interacting with agentic systems.
- name: BatchInference (Coming Soon)
description: >-
This is an asynchronous API. If the request is successful, the response will
be a job which can be polled for completion.
NOTE: This API is not yet implemented and is subject to change in concert with
other asynchronous APIs
including (post-training, evals, etc).
x-displayName: >-
Batch inference API for generating completions and chat completions.
- name: Benchmarks
- name: DatasetIO
- name: Datasets

2
docs/source/distributions/building_distro.md
View file

@ -231,7 +231,7 @@ options:
-h, --help show this help message and exit
--port PORT Port to run the server on. It can also be passed via the env var LLAMA_STACK_PORT. (default: 8321)
--image-name IMAGE_NAME
Name of the image to run. Defaults to the current conda environment (default: None)
Name of the image to run. Defaults to the current environment (default: None)
--disable-ipv6 Disable IPv6 support (default: False)
--env KEY=VALUE Environment variables to pass to the server in KEY=VALUE format. Can be specified multiple times. (default: [])
--tls-keyfile TLS_KEYFILE

88
docs/source/distributions/remote_hosted_distro/nvidia.md Normal file
View file

@ -0,0 +1,88 @@
<!-- This file was auto-generated by distro_codegen.py, please edit source -->
# NVIDIA Distribution
The `llamastack/distribution-nvidia` distribution consists of the following provider configurations.
| API | Provider(s) |
|-----|-------------|
| agents | `inline::meta-reference` |
| datasetio | `inline::localfs` |
| eval | `inline::meta-reference` |
| inference | `remote::nvidia` |
| post_training | `remote::nvidia` |
| safety | `remote::nvidia` |
| scoring | `inline::basic` |
| telemetry | `inline::meta-reference` |
| tool_runtime | `inline::rag-runtime` |
| vector_io | `inline::faiss` |
### Environment Variables
The following environment variables can be configured:
- `NVIDIA_API_KEY`: NVIDIA API Key (default: ``)
- `NVIDIA_USER_ID`: NVIDIA User ID (default: `llama-stack-user`)
- `NVIDIA_DATASET_NAMESPACE`: NVIDIA Dataset Namespace (default: `default`)
- `NVIDIA_ACCESS_POLICIES`: NVIDIA Access Policies (default: `{}`)
- `NVIDIA_PROJECT_ID`: NVIDIA Project ID (default: `test-project`)
- `NVIDIA_CUSTOMIZER_URL`: NVIDIA Customizer URL (default: `https://customizer.api.nvidia.com`)
- `NVIDIA_OUTPUT_MODEL_DIR`: NVIDIA Output Model Directory (default: `test-example-model@v1`)
- `GUARDRAILS_SERVICE_URL`: URL for the NeMo Guardrails Service (default: `http://0.0.0.0:7331`)
- `INFERENCE_MODEL`: Inference model (default: `Llama3.1-8B-Instruct`)
- `SAFETY_MODEL`: Name of the model to use for safety (default: `meta/llama-3.1-8b-instruct`)
### Models
The following models are available by default:
- `meta/llama3-8b-instruct (aliases: meta-llama/Llama-3-8B-Instruct)`
- `meta/llama3-70b-instruct (aliases: meta-llama/Llama-3-70B-Instruct)`
- `meta/llama-3.1-8b-instruct (aliases: meta-llama/Llama-3.1-8B-Instruct)`
- `meta/llama-3.1-70b-instruct (aliases: meta-llama/Llama-3.1-70B-Instruct)`
- `meta/llama-3.1-405b-instruct (aliases: meta-llama/Llama-3.1-405B-Instruct-FP8)`
- `meta/llama-3.2-1b-instruct (aliases: meta-llama/Llama-3.2-1B-Instruct)`
- `meta/llama-3.2-3b-instruct (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `meta/llama-3.2-11b-vision-instruct (aliases: meta-llama/Llama-3.2-11B-Vision-Instruct)`
- `meta/llama-3.2-90b-vision-instruct (aliases: meta-llama/Llama-3.2-90B-Vision-Instruct)`
- `nvidia/llama-3.2-nv-embedqa-1b-v2 `
- `nvidia/nv-embedqa-e5-v5 `
- `nvidia/nv-embedqa-mistral-7b-v2 `
- `snowflake/arctic-embed-l `
### Prerequisite: API Keys
Make sure you have access to a NVIDIA API Key. You can get one by visiting [https://build.nvidia.com/](https://build.nvidia.com/).
## Running Llama Stack with NVIDIA
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=8321
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v ./run.yaml:/root/my-run.yaml \
llamastack/distribution-nvidia \
--yaml-config /root/my-run.yaml \
--port $LLAMA_STACK_PORT \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
```
### Via Conda
```bash
llama stack build --template nvidia --image-type conda
llama stack run ./run.yaml \
--port 8321 \
--env NVIDIA_API_KEY=$NVIDIA_API_KEY
--env INFERENCE_MODEL=$INFERENCE_MODEL
```