phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 03:08:47 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into register_custom_model

Browse source
This commit is contained in:
Rashmi Pawar 2025-04-16 14:35:51 +05:30 • committed by GitHub
commit afb792b9c1
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
69 changed files with 8875 additions and 890 deletions
Download patch file Download diff file Expand all files Collapse all files

446
docs/_static/llama-stack-spec.html vendored
View file

@ -3096,11 +3096,18 @@
"post": {
"responses": {
"200": {
"description": "OK",
"description": "Response from an OpenAI-compatible chat completion request. **OR** Chunk from a streaming response to an OpenAI-compatible chat completion request.",
"content": {
"application/json": {
"schema": {
"$ref": "#/components/schemas/OpenAIChatCompletion"
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIChatCompletion"
},
{
"$ref": "#/components/schemas/OpenAIChatCompletionChunk"
}
]
}
}
}
@ -7889,7 +7896,13 @@
"type": "object",
"properties": {
"status": {
"type": "string"
"type": "string",
"enum": [
"OK",
"Error",
"Not Implemented"
],
"title": "HealthStatus"
}
},
"additionalProperties": false,
@ -8084,6 +8097,31 @@
}
]
}
},
"health": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
@ -8091,7 +8129,8 @@
"api",
"provider_id",
"provider_type",
"config"
"config",
"health"
],
"title": "ProviderInfo"
},
@ -8825,7 +8864,17 @@
"description": "Must be \"assistant\" to identify this as the model's response"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartParam"
}
}
],
"description": "The content of the model's response"
},
"name": {
@ -8835,9 +8884,9 @@
"tool_calls": {
"type": "array",
"items": {
"$ref": "#/components/schemas/ToolCall"
"$ref": "#/components/schemas/OpenAIChatCompletionToolCall"
},
"description": "List of tool calls. Each tool call is a ToolCall object."
"description": "List of tool calls. Each tool call is an OpenAIChatCompletionToolCall object."
}
},
"additionalProperties": false,
@ -8848,6 +8897,98 @@
"title": "OpenAIAssistantMessageParam",
"description": "A message containing the model's (assistant) response in an OpenAI-compatible chat completion request."
},
"OpenAIChatCompletionContentPartImageParam": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "image_url",
"default": "image_url"
},
"image_url": {
"$ref": "#/components/schemas/OpenAIImageURL"
}
},
"additionalProperties": false,
"required": [
"type",
"image_url"
],
"title": "OpenAIChatCompletionContentPartImageParam"
},
"OpenAIChatCompletionContentPartParam": {
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartTextParam"
},
{
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"text": "#/components/schemas/OpenAIChatCompletionContentPartTextParam",
"image_url": "#/components/schemas/OpenAIChatCompletionContentPartImageParam"
}
}
},
"OpenAIChatCompletionContentPartTextParam": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text"
},
"text": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"type",
"text"
],
"title": "OpenAIChatCompletionContentPartTextParam"
},
"OpenAIChatCompletionToolCall": {
"type": "object",
"properties": {
"index": {
"type": "integer"
},
"id": {
"type": "string"
},
"type": {
"type": "string",
"const": "function",
"default": "function"
},
"function": {
"$ref": "#/components/schemas/OpenAIChatCompletionToolCallFunction"
}
},
"additionalProperties": false,
"required": [
"type"
],
"title": "OpenAIChatCompletionToolCall"
},
"OpenAIChatCompletionToolCallFunction": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"arguments": {
"type": "string"
}
},
"additionalProperties": false,
"title": "OpenAIChatCompletionToolCallFunction"
},
"OpenAIDeveloperMessageParam": {
"type": "object",
"properties": {
@ -8858,7 +8999,17 @@
"description": "Must be \"developer\" to identify this as a developer message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartParam"
}
}
],
"description": "The content of the developer message"
},
"name": {
@ -8874,6 +9025,66 @@
"title": "OpenAIDeveloperMessageParam",
"description": "A message from the developer in an OpenAI-compatible chat completion request."
},
"OpenAIImageURL": {
"type": "object",
"properties": {
"url": {
"type": "string"
},
"detail": {
"type": "string"
}
},
"additionalProperties": false,
"required": [
"url"
],
"title": "OpenAIImageURL"
},
"OpenAIJSONSchema": {
"type": "object",
"properties": {
"name": {
"type": "string"
},
"description": {
"type": "string"
},
"strict": {
"type": "boolean"
},
"schema": {
"type": "object",
"additionalProperties": {
"oneOf": [
{
"type": "null"
},
{
"type": "boolean"
},
{
"type": "number"
},
{
"type": "string"
},
{
"type": "array"
},
{
"type": "object"
}
]
}
}
},
"additionalProperties": false,
"required": [
"name"
],
"title": "OpenAIJSONSchema"
},
"OpenAIMessageParam": {
"oneOf": [
{
@ -8903,6 +9114,76 @@
}
}
},
"OpenAIResponseFormatJSONObject": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "json_object",
"default": "json_object"
}
},
"additionalProperties": false,
"required": [
"type"
],
"title": "OpenAIResponseFormatJSONObject"
},
"OpenAIResponseFormatJSONSchema": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "json_schema",
"default": "json_schema"
},
"json_schema": {
"$ref": "#/components/schemas/OpenAIJSONSchema"
}
},
"additionalProperties": false,
"required": [
"type",
"json_schema"
],
"title": "OpenAIResponseFormatJSONSchema"
},
"OpenAIResponseFormatParam": {
"oneOf": [
{
"$ref": "#/components/schemas/OpenAIResponseFormatText"
},
{
"$ref": "#/components/schemas/OpenAIResponseFormatJSONSchema"
},
{
"$ref": "#/components/schemas/OpenAIResponseFormatJSONObject"
}
],
"discriminator": {
"propertyName": "type",
"mapping": {
"text": "#/components/schemas/OpenAIResponseFormatText",
"json_schema": "#/components/schemas/OpenAIResponseFormatJSONSchema",
"json_object": "#/components/schemas/OpenAIResponseFormatJSONObject"
}
}
},
"OpenAIResponseFormatText": {
"type": "object",
"properties": {
"type": {
"type": "string",
"const": "text",
"default": "text"
}
},
"additionalProperties": false,
"required": [
"type"
],
"title": "OpenAIResponseFormatText"
},
"OpenAISystemMessageParam": {
"type": "object",
"properties": {
@ -8913,7 +9194,17 @@
"description": "Must be \"system\" to identify this as a system message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartParam"
}
}
],
"description": "The content of the \"system prompt\". If multiple system messages are provided, they are concatenated. The underlying Llama Stack code may also add other system messages (for example, for formatting tool definitions)."
},
"name": {
@ -8943,7 +9234,17 @@
"description": "Unique identifier for the tool call this response is for"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartParam"
}
}
],
"description": "The response content from the tool"
}
},
@ -8966,7 +9267,17 @@
"description": "Must be \"user\" to identify this as a user message"
},
"content": {
"$ref": "#/components/schemas/InterleavedContent",
"oneOf": [
{
"type": "string"
},
{
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionContentPartParam"
}
}
],
"description": "The content of the message, which can include text and other media"
},
"name": {
@ -9094,10 +9405,7 @@
"description": "(Optional) The penalty for repeated tokens"
},
"response_format": {
"type": "object",
"additionalProperties": {
"type": "string"
},
"$ref": "#/components/schemas/OpenAIResponseFormatParam",
"description": "(Optional) The response format to use"
},
"seed": {
@ -9274,6 +9582,46 @@
"title": "OpenAIChatCompletion",
"description": "Response from an OpenAI-compatible chat completion request."
},
"OpenAIChatCompletionChunk": {
"type": "object",
"properties": {
"id": {
"type": "string",
"description": "The ID of the chat completion"
},
"choices": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChunkChoice"
},
"description": "List of choices"
},
"object": {
"type": "string",
"const": "chat.completion.chunk",
"default": "chat.completion.chunk",
"description": "The object type, which will be \"chat.completion.chunk\""
},
"created": {
"type": "integer",
"description": "The Unix timestamp in seconds when the chat completion was created"
},
"model": {
"type": "string",
"description": "The model that was used to generate the chat completion"
}
},
"additionalProperties": false,
"required": [
"id",
"choices",
"object",
"created",
"model"
],
"title": "OpenAIChatCompletionChunk",
"description": "Chunk from a streaming response to an OpenAI-compatible chat completion request."
},
"OpenAIChoice": {
"type": "object",
"properties": {
@ -9286,10 +9634,12 @@
"description": "The reason the model stopped generating"
},
"index": {
"type": "integer"
"type": "integer",
"description": "The index of the choice"
},
"logprobs": {
"$ref": "#/components/schemas/OpenAIChoiceLogprobs"
"$ref": "#/components/schemas/OpenAIChoiceLogprobs",
"description": "(Optional) The log probabilities for the tokens in the message"
}
},
"additionalProperties": false,
@ -9301,6 +9651,33 @@
"title": "OpenAIChoice",
"description": "A choice from an OpenAI-compatible chat completion response."
},
"OpenAIChoiceDelta": {
"type": "object",
"properties": {
"content": {
"type": "string",
"description": "(Optional) The content of the delta"
},
"refusal": {
"type": "string",
"description": "(Optional) The refusal of the delta"
},
"role": {
"type": "string",
"description": "(Optional) The role of the delta"
},
"tool_calls": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAIChatCompletionToolCall"
},
"description": "(Optional) The tool calls of the delta"
}
},
"additionalProperties": false,
"title": "OpenAIChoiceDelta",
"description": "A delta from an OpenAI-compatible chat completion streaming response."
},
"OpenAIChoiceLogprobs": {
"type": "object",
"properties": {
@ -9308,19 +9685,50 @@
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAITokenLogProb"
}
},
"description": "(Optional) The log probabilities for the tokens in the message"
},
"refusal": {
"type": "array",
"items": {
"$ref": "#/components/schemas/OpenAITokenLogProb"
}
},
"description": "(Optional) The log probabilities for the tokens in the message"
}
},
"additionalProperties": false,
"title": "OpenAIChoiceLogprobs",
"description": "The log probabilities for the tokens in the message from an OpenAI-compatible chat completion response."
},
"OpenAIChunkChoice": {
"type": "object",
"properties": {
"delta": {
"$ref": "#/components/schemas/OpenAIChoiceDelta",
"description": "The delta from the chunk"
},
"finish_reason": {
"type": "string",
"description": "The reason the model stopped generating"
},
"index": {
"type": "integer",
"description": "The index of the choice"
},
"logprobs": {
"$ref": "#/components/schemas/OpenAIChoiceLogprobs",
"description": "(Optional) The log probabilities for the tokens in the message"
}
},
"additionalProperties": false,
"required": [
"delta",
"finish_reason",
"index"
],
"title": "OpenAIChunkChoice",
"description": "A chunk choice from an OpenAI-compatible chat completion streaming response."
},
"OpenAITokenLogProb": {
"type": "object",
"properties": {

295
docs/_static/llama-stack-spec.yaml vendored
View file

@ -2135,11 +2135,15 @@ paths:
post:
responses:
'200':
description: OK
description: >-
Response from an OpenAI-compatible chat completion request. **OR** Chunk
from a streaming response to an OpenAI-compatible chat completion request.
content:
application/json:
schema:
$ref: '#/components/schemas/OpenAIChatCompletion'
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletion'
- $ref: '#/components/schemas/OpenAIChatCompletionChunk'
'400':
$ref: '#/components/responses/BadRequest400'
'429':
@ -5463,6 +5467,11 @@ components:
properties:
status:
type: string
enum:
- OK
- Error
- Not Implemented
title: HealthStatus
additionalProperties: false
required:
- status
@ -5574,12 +5583,23 @@ 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
@ -6057,7 +6077,11 @@ components:
description: >-
Must be "assistant" to identify this as the model's response
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the model's response
name:
type: string
@ -6066,9 +6090,10 @@ components:
tool_calls:
type: array
items:
$ref: '#/components/schemas/ToolCall'
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: >-
List of tool calls. Each tool call is a ToolCall object.
List of tool calls. Each tool call is an OpenAIChatCompletionToolCall
object.
additionalProperties: false
required:
- role
@ -6077,6 +6102,70 @@ components:
description: >-
A message containing the model's (assistant) response in an OpenAI-compatible
chat completion request.
"OpenAIChatCompletionContentPartImageParam":
type: object
properties:
type:
type: string
const: image_url
default: image_url
image_url:
$ref: '#/components/schemas/OpenAIImageURL'
additionalProperties: false
required:
- type
- image_url
title: >-
OpenAIChatCompletionContentPartImageParam
OpenAIChatCompletionContentPartParam:
oneOf:
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
- $ref: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIChatCompletionContentPartTextParam'
image_url: '#/components/schemas/OpenAIChatCompletionContentPartImageParam'
OpenAIChatCompletionContentPartTextParam:
type: object
properties:
type:
type: string
const: text
default: text
text:
type: string
additionalProperties: false
required:
- type
- text
title: OpenAIChatCompletionContentPartTextParam
OpenAIChatCompletionToolCall:
type: object
properties:
index:
type: integer
id:
type: string
type:
type: string
const: function
default: function
function:
$ref: '#/components/schemas/OpenAIChatCompletionToolCallFunction'
additionalProperties: false
required:
- type
title: OpenAIChatCompletionToolCall
OpenAIChatCompletionToolCallFunction:
type: object
properties:
name:
type: string
arguments:
type: string
additionalProperties: false
title: OpenAIChatCompletionToolCallFunction
OpenAIDeveloperMessageParam:
type: object
properties:
@ -6087,7 +6176,11 @@ components:
description: >-
Must be "developer" to identify this as a developer message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The content of the developer message
name:
type: string
@ -6100,6 +6193,40 @@ components:
title: OpenAIDeveloperMessageParam
description: >-
A message from the developer in an OpenAI-compatible chat completion request.
OpenAIImageURL:
type: object
properties:
url:
type: string
detail:
type: string
additionalProperties: false
required:
- url
title: OpenAIImageURL
OpenAIJSONSchema:
type: object
properties:
name:
type: string
description:
type: string
strict:
type: boolean
schema:
type: object
additionalProperties:
oneOf:
- type: 'null'
- type: boolean
- type: number
- type: string
- type: array
- type: object
additionalProperties: false
required:
- name
title: OpenAIJSONSchema
OpenAIMessageParam:
oneOf:
- $ref: '#/components/schemas/OpenAIUserMessageParam'
@ -6115,6 +6242,53 @@ components:
assistant: '#/components/schemas/OpenAIAssistantMessageParam'
tool: '#/components/schemas/OpenAIToolMessageParam'
developer: '#/components/schemas/OpenAIDeveloperMessageParam'
OpenAIResponseFormatJSONObject:
type: object
properties:
type:
type: string
const: json_object
default: json_object
additionalProperties: false
required:
- type
title: OpenAIResponseFormatJSONObject
OpenAIResponseFormatJSONSchema:
type: object
properties:
type:
type: string
const: json_schema
default: json_schema
json_schema:
$ref: '#/components/schemas/OpenAIJSONSchema'
additionalProperties: false
required:
- type
- json_schema
title: OpenAIResponseFormatJSONSchema
OpenAIResponseFormatParam:
oneOf:
- $ref: '#/components/schemas/OpenAIResponseFormatText'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONSchema'
- $ref: '#/components/schemas/OpenAIResponseFormatJSONObject'
discriminator:
propertyName: type
mapping:
text: '#/components/schemas/OpenAIResponseFormatText'
json_schema: '#/components/schemas/OpenAIResponseFormatJSONSchema'
json_object: '#/components/schemas/OpenAIResponseFormatJSONObject'
OpenAIResponseFormatText:
type: object
properties:
type:
type: string
const: text
default: text
additionalProperties: false
required:
- type
title: OpenAIResponseFormatText
OpenAISystemMessageParam:
type: object
properties:
@ -6125,7 +6299,11 @@ components:
description: >-
Must be "system" to identify this as a system message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: >-
The content of the "system prompt". If multiple system messages are provided,
they are concatenated. The underlying Llama Stack code may also add other
@ -6155,7 +6333,11 @@ components:
description: >-
Unique identifier for the tool call this response is for
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: The response content from the tool
additionalProperties: false
required:
@ -6176,7 +6358,11 @@ components:
description: >-
Must be "user" to identify this as a user message
content:
$ref: '#/components/schemas/InterleavedContent'
oneOf:
- type: string
- type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionContentPartParam'
description: >-
The content of the message, which can include text and other media
name:
@ -6262,9 +6448,7 @@ components:
description: >-
(Optional) The penalty for repeated tokens
response_format:
type: object
additionalProperties:
type: string
$ref: '#/components/schemas/OpenAIResponseFormatParam'
description: (Optional) The response format to use
seed:
type: integer
@ -6370,6 +6554,41 @@ components:
title: OpenAIChatCompletion
description: >-
Response from an OpenAI-compatible chat completion request.
OpenAIChatCompletionChunk:
type: object
properties:
id:
type: string
description: The ID of the chat completion
choices:
type: array
items:
$ref: '#/components/schemas/OpenAIChunkChoice'
description: List of choices
object:
type: string
const: chat.completion.chunk
default: chat.completion.chunk
description: >-
The object type, which will be "chat.completion.chunk"
created:
type: integer
description: >-
The Unix timestamp in seconds when the chat completion was created
model:
type: string
description: >-
The model that was used to generate the chat completion
additionalProperties: false
required:
- id
- choices
- object
- created
- model
title: OpenAIChatCompletionChunk
description: >-
Chunk from a streaming response to an OpenAI-compatible chat completion request.
OpenAIChoice:
type: object
properties:
@ -6381,8 +6600,11 @@ components:
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- message
@ -6391,6 +6613,27 @@ components:
title: OpenAIChoice
description: >-
A choice from an OpenAI-compatible chat completion response.
OpenAIChoiceDelta:
type: object
properties:
content:
type: string
description: (Optional) The content of the delta
refusal:
type: string
description: (Optional) The refusal of the delta
role:
type: string
description: (Optional) The role of the delta
tool_calls:
type: array
items:
$ref: '#/components/schemas/OpenAIChatCompletionToolCall'
description: (Optional) The tool calls of the delta
additionalProperties: false
title: OpenAIChoiceDelta
description: >-
A delta from an OpenAI-compatible chat completion streaming response.
OpenAIChoiceLogprobs:
type: object
properties:
@ -6398,15 +6641,43 @@ components:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
refusal:
type: array
items:
$ref: '#/components/schemas/OpenAITokenLogProb'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
title: OpenAIChoiceLogprobs
description: >-
The log probabilities for the tokens in the message from an OpenAI-compatible
chat completion response.
OpenAIChunkChoice:
type: object
properties:
delta:
$ref: '#/components/schemas/OpenAIChoiceDelta'
description: The delta from the chunk
finish_reason:
type: string
description: The reason the model stopped generating
index:
type: integer
description: The index of the choice
logprobs:
$ref: '#/components/schemas/OpenAIChoiceLogprobs'
description: >-
(Optional) The log probabilities for the tokens in the message
additionalProperties: false
required:
- delta
- finish_reason
- index
title: OpenAIChunkChoice
description: >-
A chunk choice from an OpenAI-compatible chat completion streaming response.
OpenAITokenLogProb:
type: object
properties:

12
docs/source/distributions/ondevice_distro/android_sdk.md
View file

@ -24,7 +24,7 @@ The key files in the app are `ExampleLlamaStackLocalInference.kt`, `ExampleLlama
Add the following dependency in your `build.gradle.kts` file:
```
dependencies {
implementation("com.llama.llamastack:llama-stack-client-kotlin:0.1.4.2")
implementation("com.llama.llamastack:llama-stack-client-kotlin:0.2.2")
}
```
This will download jar files in your gradle cache in a directory like `~/.gradle/caches/modules-2/files-2.1/com.llama.llamastack/`
@ -37,11 +37,7 @@ For local inferencing, it is required to include the ExecuTorch library into you
Include the ExecuTorch library by:
1. Download the `download-prebuilt-et-lib.sh` script file from the [llama-stack-client-kotlin-client-local](https://github.com/meta-llama/llama-stack-client-kotlin/tree/latest-release/llama-stack-client-kotlin-client-local/download-prebuilt-et-lib.sh) directory to your local machine.
2. Move the script to the top level of your Android app where the app directory resides:
<p align="center">
<img src="https://github.com/meta-llama/llama-stack-client-kotlin/blob/latest-release/doc/img/example_android_app_directory.png" style="width:300px">
</p>
2. Move the script to the top level of your Android app where the `app` directory resides.
3. Run `sh download-prebuilt-et-lib.sh` to create an `app/libs` directory and download the `executorch.aar` in that path. This generates an ExecuTorch library for the XNNPACK delegate.
4. Add the `executorch.aar` dependency in your `build.gradle.kts` file:
```
@ -52,6 +48,8 @@ dependencies {
}
```
See other dependencies for the local RAG in Android app [README](https://github.com/meta-llama/llama-stack-client-kotlin/tree/latest-release/examples/android_app#quick-start).
## Llama Stack APIs in Your Android App
Breaking down the demo app, this section will show the core pieces that are used to initialize and run inference with Llama Stack using the Kotlin library.
@ -60,7 +58,7 @@ Start a Llama Stack server on localhost. Here is an example of how you can do th
```
conda create -n stack-fireworks python=3.10
conda activate stack-fireworks
pip install --no-cache llama-stack==0.1.4
pip install --no-cache llama-stack==0.2.2
llama stack build --template fireworks --image-type conda
export FIREWORKS_API_KEY=<SOME_KEY>
llama stack run fireworks --port 5050

2
docs/source/distributions/self_hosted_distro/groq.md
View file

@ -43,7 +43,9 @@ The following models are available by default:
- `groq/llama-3.3-70b-versatile (aliases: meta-llama/Llama-3.3-70B-Instruct)`
- `groq/llama-3.2-3b-preview (aliases: meta-llama/Llama-3.2-3B-Instruct)`
- `groq/llama-4-scout-17b-16e-instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
- `groq/meta-llama/llama-4-scout-17b-16e-instruct (aliases: meta-llama/Llama-4-Scout-17B-16E-Instruct)`
- `groq/llama-4-maverick-17b-128e-instruct (aliases: meta-llama/Llama-4-Maverick-17B-128E-Instruct)`
- `groq/meta-llama/llama-4-maverick-17b-128e-instruct (aliases: meta-llama/Llama-4-Maverick-17B-128E-Instruct)`
### Prerequisite: API Keys

51
docs/source/distributions/self_hosted_distro/remote-vllm.md
View file

@ -41,7 +41,7 @@ The following environment variables can be configured:
## Setting up vLLM server
In the following sections, we'll use either AMD and NVIDIA GPUs to serve as hardware accelerators for the vLLM
In the following sections, we'll use AMD, NVIDIA or Intel GPUs to serve as hardware accelerators for the vLLM
server, which acts as both the LLM inference provider and the safety provider. Note that vLLM also
[supports many other hardware accelerators](https://docs.vllm.ai/en/latest/getting_started/installation.html) and
that we only use GPUs here for demonstration purposes.
@ -162,6 +162,55 @@ docker run \
--port $SAFETY_PORT
```
### Setting up vLLM server on Intel GPU
Refer to [vLLM Documentation for XPU](https://docs.vllm.ai/en/v0.8.2/getting_started/installation/gpu.html?device=xpu) to get a vLLM endpoint. In addition to vLLM side setup which guides towards installing vLLM from sources orself-building vLLM Docker container, Intel provides prebuilt vLLM container to use on systems with Intel GPUs supported by PyTorch XPU backend:
- [intel/vllm](https://hub.docker.com/r/intel/vllm)
Here is a sample script to start a vLLM server locally via Docker using Intel provided container:
```bash
export INFERENCE_PORT=8000
export INFERENCE_MODEL=meta-llama/Llama-3.2-1B-Instruct
export ZE_AFFINITY_MASK=0
docker run \
--pull always \
--device /dev/dri \
-v /dev/dri/by-path:/dev/dri/by-path \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
--env ZE_AFFINITY_MASK=$ZE_AFFINITY_MASK \
-p $INFERENCE_PORT:$INFERENCE_PORT \
--ipc=host \
intel/vllm:xpu \
--gpu-memory-utilization 0.7 \
--model $INFERENCE_MODEL \
--port $INFERENCE_PORT
```
If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a vLLM with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
```bash
export SAFETY_PORT=8081
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export ZE_AFFINITY_MASK=1
docker run \
--pull always \
--device /dev/dri \
-v /dev/dri/by-path:/dev/dri/by-path \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
--env ZE_AFFINITY_MASK=$ZE_AFFINITY_MASK \
-p $SAFETY_PORT:$SAFETY_PORT \
--ipc=host \
intel/vllm:xpu \
--gpu-memory-utilization 0.7 \
--model $SAFETY_MODEL \
--port $SAFETY_PORT
```
## Running Llama Stack
Now you are ready to run Llama Stack with vLLM as the inference provider. You can do this via Conda (build code) or Docker which has a pre-built image.