Skip to content
Draft
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
187 changes: 71 additions & 116 deletions training/api-reference/openapi.json
Original file line number Diff line number Diff line change
Expand Up @@ -2030,28 +2030,6 @@
"title": "Request Id",
"description": "The request_id related to this request. If the caller does not set it, a random_uuid will be generated. This id is used through out the inference process and return in response."
},
"logits_processors": {
"anyOf": [
{
"items": {
"anyOf": [
{
"type": "string"
},
{
"$ref": "#/components/schemas/LogitsProcessorConstructor"
}
]
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Logits Processors",
"description": "A list of either qualified names of logits processors, or constructor objects, to apply when sampling. A constructor is a JSON object with a required 'qualname' field specifying the qualified name of the processor class/factory, and optional 'args' and 'kwargs' fields containing positional and keyword arguments. For example: {'qualname': 'my_module.MyLogitsProcessor', 'args': [1, 2], 'kwargs': {'param': 'value'}}."
},
"return_tokens_as_token_ids": {
"anyOf": [
{
Expand Down Expand Up @@ -2141,6 +2119,17 @@
],
"title": "Vllm Xargs",
"description": "Additional request parameters with (list of) string or numeric values, used by custom extensions."
},
"repetition_detection": {
"anyOf": [
{
"$ref": "#/components/schemas/RepetitionDetectionParams"
},
{
"type": "null"
}
],
"description": "Parameters for detecting repetitive N-gram patterns in output tokens. If such repetition is detected, generation will be ended early. LLMs can sometimes generate repetitive, unhelpful token patterns, stopping only when they hit the maximum output length (e.g. 'abcdabcdabcd...' or '\\emoji \\emoji \\emoji ...'). This feature can detect such behavior and terminate early, saving time and tokens."
}
},
"additionalProperties": true,
Expand Down Expand Up @@ -2458,7 +2447,7 @@
"default": "function"
},
"function": {
"$ref": "#/components/schemas/vllm__entrypoints__openai__engine__protocol__FunctionDefinition"
"$ref": "#/components/schemas/FunctionDefinition"
}
},
"additionalProperties": true,
Expand Down Expand Up @@ -2591,17 +2580,6 @@
}
],
"title": "Reasoning"
},
"reasoning_content": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Reasoning Content"
}
},
"additionalProperties": true,
Expand Down Expand Up @@ -3342,6 +3320,43 @@
],
"title": "FunctionCall"
},
"FunctionDefinition": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Description"
},
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Parameters"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"name"
],
"title": "FunctionDefinition"
},
"HTTPValidationError": {
"properties": {
"detail": {
Expand Down Expand Up @@ -3585,44 +3600,6 @@
"title": "LogRequest",
"description": "Schema for logging trajectories."
},
"LogitsProcessorConstructor": {
"properties": {
"qualname": {
"type": "string",
"title": "Qualname"
},
"args": {
"anyOf": [
{
"items": {},
"type": "array"
},
{
"type": "null"
}
],
"title": "Args"
},
"kwargs": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Kwargs"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"qualname"
],
"title": "LogitsProcessorConstructor"
},
"Logprob": {
"properties": {
"logprob": {
Expand Down Expand Up @@ -3913,6 +3890,28 @@
"type": "object",
"title": "PromptTokenUsageInfo"
},
"RepetitionDetectionParams": {
"properties": {
"max_pattern_size": {
"type": "integer",
"title": "Max Pattern Size",
"default": 0
},
"min_pattern_size": {
"type": "integer",
"title": "Min Pattern Size",
"default": 0
},
"min_count": {
"type": "integer",
"title": "Min Count",
"default": 0
}
},
"type": "object",
"title": "RepetitionDetectionParams",
"description": "Parameters for detecting repetitive N-gram patterns in output tokens."
},
"ResponseFormat": {
"properties": {
"type": {
Expand Down Expand Up @@ -4489,13 +4488,6 @@
"type": {
"type": "string",
"title": "Error Type"
},
"input": {
"title": "Input"
},
"ctx": {
"type": "object",
"title": "Context"
}
},
"type": "object",
Expand Down Expand Up @@ -4553,43 +4545,6 @@
"name"
],
"title": "FunctionDefinition"
},
"vllm__entrypoints__openai__engine__protocol__FunctionDefinition": {
"properties": {
"name": {
"type": "string",
"title": "Name"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Description"
},
"parameters": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Parameters"
}
},
"additionalProperties": true,
"type": "object",
"required": [
"name"
],
"title": "FunctionDefinition"
}
},
"securitySchemes": {
Expand Down