mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-20 14:22:08 +00:00
09eca64227
# What does this PR do? <!-- Congratulations! You've made it this far! You're not quite done yet though. Once merged, your PR is going to appear in the release notes with the title you set, so make sure it's a great title that fully reflects the extent of your awesome contribution. Then, please replace this with a description of the change and which issue is fixed (if applicable). Please also include relevant motivation and context. List any dependencies (if any) that are required for this change. Once you're done, someone will review your PR shortly (see the section "Who can review?" below to tag some potential reviewers). They may suggest changes to make the code even better. If no one reviewed your PR after a week has passed, don't hesitate to post a new comment @-mentioning the same persons---sometimes notifications get lost. --> <!-- Remove if not applicable --> Fixes # (issue) ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Did you read the [contributor guideline](https://github.com/huggingface/transformers/blob/main/CONTRIBUTING.md#start-contributing-pull-requests), Pull Request section? - [ ] Was this discussed/approved via a Github issue or the [forum](https://discuss.huggingface.co/)? Please add a link to it if that's the case. - [ ] Did you make sure to update the documentation with your changes? Here are the [documentation guidelines](https://github.com/huggingface/transformers/tree/main/docs), and [here are tips on formatting docstrings](https://github.com/huggingface/transformers/tree/main/docs#writing-source-documentation). - [ ] Did you write any new necessary tests? ## Who can review? Anyone in the community is free to review the PR once the tests have passed. Feel free to tag members/contributors who may be interested in your PR. <!-- Your PR will be replied to more quickly if you can figure out the right person to tag with @ @OlivierDehaene OR @Narsil -->
850 lines
22 KiB
JSON
850 lines
22 KiB
JSON
{
|
|
"openapi": "3.0.3",
|
|
"info": {
|
|
"title": "Text Generation Inference",
|
|
"description": "Text Generation Webserver",
|
|
"contact": {
|
|
"name": "Olivier Dehaene"
|
|
},
|
|
"license": {
|
|
"name": "Apache 2.0",
|
|
"url": "https://www.apache.org/licenses/LICENSE-2.0"
|
|
},
|
|
"version": "1.0.1"
|
|
},
|
|
"paths": {
|
|
"/": {
|
|
"post": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Generate tokens if `stream == false` or a stream of token if `stream == true`",
|
|
"description": "Generate tokens if `stream == false` or a stream of token if `stream == true`",
|
|
"operationId": "compat_generate",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/CompatGenerateRequest"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Generated Text",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/GenerateResponse"
|
|
}
|
|
},
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/StreamResponse"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Input validation error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Input validation error"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"424": {
|
|
"description": "Generation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Request failed during generation"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"429": {
|
|
"description": "Model is overloaded",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Model is overloaded"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"500": {
|
|
"description": "Incomplete generation",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Incomplete generation"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/generate": {
|
|
"post": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Generate tokens",
|
|
"description": "Generate tokens",
|
|
"operationId": "generate",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/GenerateRequest"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Generated Text",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/GenerateResponse"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Input validation error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Input validation error"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"424": {
|
|
"description": "Generation Error",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Request failed during generation"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"429": {
|
|
"description": "Model is overloaded",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Model is overloaded"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"500": {
|
|
"description": "Incomplete generation",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Incomplete generation"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/generate_stream": {
|
|
"post": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Generate a stream of token using Server-Sent Events",
|
|
"description": "Generate a stream of token using Server-Sent Events",
|
|
"operationId": "generate_stream",
|
|
"requestBody": {
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/GenerateRequest"
|
|
}
|
|
}
|
|
},
|
|
"required": true
|
|
},
|
|
"responses": {
|
|
"200": {
|
|
"description": "Generated Text",
|
|
"content": {
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/StreamResponse"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"422": {
|
|
"description": "Input validation error",
|
|
"content": {
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Input validation error"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"424": {
|
|
"description": "Generation Error",
|
|
"content": {
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Request failed during generation"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"429": {
|
|
"description": "Model is overloaded",
|
|
"content": {
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Model is overloaded"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"500": {
|
|
"description": "Incomplete generation",
|
|
"content": {
|
|
"text/event-stream": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "Incomplete generation"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/health": {
|
|
"get": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Health check method",
|
|
"description": "Health check method",
|
|
"operationId": "health",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Everything is working fine"
|
|
},
|
|
"503": {
|
|
"description": "Text generation inference is down",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/ErrorResponse"
|
|
},
|
|
"example": {
|
|
"error": "unhealthy",
|
|
"error_type": "healthcheck"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/info": {
|
|
"get": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Text Generation Inference endpoint info",
|
|
"description": "Text Generation Inference endpoint info",
|
|
"operationId": "get_model_info",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Served model info",
|
|
"content": {
|
|
"application/json": {
|
|
"schema": {
|
|
"$ref": "#/components/schemas/Info"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"/metrics": {
|
|
"get": {
|
|
"tags": [
|
|
"Text Generation Inference"
|
|
],
|
|
"summary": "Prometheus metrics scrape endpoint",
|
|
"description": "Prometheus metrics scrape endpoint",
|
|
"operationId": "metrics",
|
|
"responses": {
|
|
"200": {
|
|
"description": "Prometheus Metrics",
|
|
"content": {
|
|
"text/plain": {
|
|
"schema": {
|
|
"type": "string"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"components": {
|
|
"schemas": {
|
|
"BestOfSequence": {
|
|
"type": "object",
|
|
"required": [
|
|
"generated_text",
|
|
"finish_reason",
|
|
"generated_tokens",
|
|
"prefill",
|
|
"tokens"
|
|
],
|
|
"properties": {
|
|
"finish_reason": {
|
|
"$ref": "#/components/schemas/FinishReason"
|
|
},
|
|
"generated_text": {
|
|
"type": "string",
|
|
"example": "test"
|
|
},
|
|
"generated_tokens": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": 1,
|
|
"minimum": 0.0
|
|
},
|
|
"prefill": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/PrefillToken"
|
|
}
|
|
},
|
|
"seed": {
|
|
"type": "integer",
|
|
"format": "int64",
|
|
"example": 42,
|
|
"nullable": true,
|
|
"minimum": 0.0
|
|
},
|
|
"tokens": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/Token"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"CompatGenerateRequest": {
|
|
"type": "object",
|
|
"required": [
|
|
"inputs"
|
|
],
|
|
"properties": {
|
|
"inputs": {
|
|
"type": "string",
|
|
"example": "My name is Olivier and I"
|
|
},
|
|
"parameters": {
|
|
"$ref": "#/components/schemas/GenerateParameters"
|
|
},
|
|
"stream": {
|
|
"type": "boolean",
|
|
"default": "false"
|
|
}
|
|
}
|
|
},
|
|
"Details": {
|
|
"type": "object",
|
|
"required": [
|
|
"finish_reason",
|
|
"generated_tokens",
|
|
"prefill",
|
|
"tokens"
|
|
],
|
|
"properties": {
|
|
"best_of_sequences": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/BestOfSequence"
|
|
},
|
|
"nullable": true
|
|
},
|
|
"finish_reason": {
|
|
"$ref": "#/components/schemas/FinishReason"
|
|
},
|
|
"generated_tokens": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": 1,
|
|
"minimum": 0.0
|
|
},
|
|
"prefill": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/PrefillToken"
|
|
}
|
|
},
|
|
"seed": {
|
|
"type": "integer",
|
|
"format": "int64",
|
|
"example": 42,
|
|
"nullable": true,
|
|
"minimum": 0.0
|
|
},
|
|
"tokens": {
|
|
"type": "array",
|
|
"items": {
|
|
"$ref": "#/components/schemas/Token"
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"ErrorResponse": {
|
|
"type": "object",
|
|
"required": [
|
|
"error",
|
|
"error_type"
|
|
],
|
|
"properties": {
|
|
"error": {
|
|
"type": "string"
|
|
},
|
|
"error_type": {
|
|
"type": "string"
|
|
}
|
|
}
|
|
},
|
|
"FinishReason": {
|
|
"type": "string",
|
|
"enum": [
|
|
"length",
|
|
"eos_token",
|
|
"stop_sequence"
|
|
]
|
|
},
|
|
"GenerateParameters": {
|
|
"type": "object",
|
|
"properties": {
|
|
"best_of": {
|
|
"type": "integer",
|
|
"default": "null",
|
|
"example": 1,
|
|
"nullable": true,
|
|
"minimum": 0.0,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"decoder_input_details": {
|
|
"type": "boolean",
|
|
"default": "true"
|
|
},
|
|
"details": {
|
|
"type": "boolean",
|
|
"default": "true"
|
|
},
|
|
"do_sample": {
|
|
"type": "boolean",
|
|
"default": "false",
|
|
"example": true
|
|
},
|
|
"max_new_tokens": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"default": "20",
|
|
"minimum": 0.0,
|
|
"exclusiveMaximum": 512.0,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"repetition_penalty": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"default": "null",
|
|
"example": 1.03,
|
|
"nullable": true,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"return_full_text": {
|
|
"type": "boolean",
|
|
"default": "null",
|
|
"example": false,
|
|
"nullable": true
|
|
},
|
|
"seed": {
|
|
"type": "integer",
|
|
"format": "int64",
|
|
"default": "null",
|
|
"example": "null",
|
|
"nullable": true,
|
|
"minimum": 0.0,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"stop": {
|
|
"type": "array",
|
|
"items": {
|
|
"type": "string"
|
|
},
|
|
"example": [
|
|
"photographer"
|
|
],
|
|
"maxItems": 4
|
|
},
|
|
"temperature": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"default": "null",
|
|
"example": 0.5,
|
|
"nullable": true,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"top_k": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"default": "null",
|
|
"example": 10,
|
|
"nullable": true,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"top_p": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"default": "null",
|
|
"example": 0.95,
|
|
"nullable": true,
|
|
"maximum": 1.0,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"truncate": {
|
|
"type": "integer",
|
|
"default": "null",
|
|
"example": "null",
|
|
"nullable": true,
|
|
"minimum": 0.0
|
|
},
|
|
"typical_p": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"default": "null",
|
|
"example": 0.95,
|
|
"nullable": true,
|
|
"maximum": 1.0,
|
|
"exclusiveMinimum": 0.0
|
|
},
|
|
"watermark": {
|
|
"type": "boolean",
|
|
"default": "false",
|
|
"example": true
|
|
}
|
|
}
|
|
},
|
|
"GenerateRequest": {
|
|
"type": "object",
|
|
"required": [
|
|
"inputs"
|
|
],
|
|
"properties": {
|
|
"inputs": {
|
|
"type": "string",
|
|
"example": "My name is Olivier and I"
|
|
},
|
|
"parameters": {
|
|
"$ref": "#/components/schemas/GenerateParameters"
|
|
}
|
|
}
|
|
},
|
|
"GenerateResponse": {
|
|
"type": "object",
|
|
"required": [
|
|
"generated_text"
|
|
],
|
|
"properties": {
|
|
"details": {
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/components/schemas/Details"
|
|
}
|
|
],
|
|
"nullable": true
|
|
},
|
|
"generated_text": {
|
|
"type": "string",
|
|
"example": "test"
|
|
}
|
|
}
|
|
},
|
|
"Info": {
|
|
"type": "object",
|
|
"required": [
|
|
"model_id",
|
|
"model_dtype",
|
|
"model_device_type",
|
|
"max_concurrent_requests",
|
|
"max_best_of",
|
|
"max_stop_sequences",
|
|
"max_input_length",
|
|
"max_total_tokens",
|
|
"waiting_served_ratio",
|
|
"max_batch_total_tokens",
|
|
"max_waiting_tokens",
|
|
"validation_workers",
|
|
"version"
|
|
],
|
|
"properties": {
|
|
"docker_label": {
|
|
"type": "string",
|
|
"example": "null",
|
|
"nullable": true
|
|
},
|
|
"max_batch_total_tokens": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": "32000",
|
|
"minimum": 0.0
|
|
},
|
|
"max_best_of": {
|
|
"type": "integer",
|
|
"example": "2",
|
|
"minimum": 0.0
|
|
},
|
|
"max_concurrent_requests": {
|
|
"type": "integer",
|
|
"description": "Router Parameters",
|
|
"example": "128",
|
|
"minimum": 0.0
|
|
},
|
|
"max_input_length": {
|
|
"type": "integer",
|
|
"example": "1024",
|
|
"minimum": 0.0
|
|
},
|
|
"max_stop_sequences": {
|
|
"type": "integer",
|
|
"example": "4",
|
|
"minimum": 0.0
|
|
},
|
|
"max_total_tokens": {
|
|
"type": "integer",
|
|
"example": "2048",
|
|
"minimum": 0.0
|
|
},
|
|
"max_waiting_tokens": {
|
|
"type": "integer",
|
|
"example": "20",
|
|
"minimum": 0.0
|
|
},
|
|
"model_device_type": {
|
|
"type": "string",
|
|
"example": "cuda"
|
|
},
|
|
"model_dtype": {
|
|
"type": "string",
|
|
"example": "torch.float16"
|
|
},
|
|
"model_id": {
|
|
"type": "string",
|
|
"description": "Model info",
|
|
"example": "bigscience/blomm-560m"
|
|
},
|
|
"model_pipeline_tag": {
|
|
"type": "string",
|
|
"example": "text-generation",
|
|
"nullable": true
|
|
},
|
|
"model_sha": {
|
|
"type": "string",
|
|
"example": "e985a63cdc139290c5f700ff1929f0b5942cced2",
|
|
"nullable": true
|
|
},
|
|
"sha": {
|
|
"type": "string",
|
|
"example": "null",
|
|
"nullable": true
|
|
},
|
|
"validation_workers": {
|
|
"type": "integer",
|
|
"example": "2",
|
|
"minimum": 0.0
|
|
},
|
|
"version": {
|
|
"type": "string",
|
|
"description": "Router Info",
|
|
"example": "0.5.0"
|
|
},
|
|
"waiting_served_ratio": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"example": "1.2"
|
|
}
|
|
}
|
|
},
|
|
"PrefillToken": {
|
|
"type": "object",
|
|
"required": [
|
|
"id",
|
|
"text",
|
|
"logprob"
|
|
],
|
|
"properties": {
|
|
"id": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": 0,
|
|
"minimum": 0.0
|
|
},
|
|
"logprob": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"example": -0.34,
|
|
"nullable": true
|
|
},
|
|
"text": {
|
|
"type": "string",
|
|
"example": "test"
|
|
}
|
|
}
|
|
},
|
|
"StreamDetails": {
|
|
"type": "object",
|
|
"required": [
|
|
"finish_reason",
|
|
"generated_tokens"
|
|
],
|
|
"properties": {
|
|
"finish_reason": {
|
|
"$ref": "#/components/schemas/FinishReason"
|
|
},
|
|
"generated_tokens": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": 1,
|
|
"minimum": 0.0
|
|
},
|
|
"seed": {
|
|
"type": "integer",
|
|
"format": "int64",
|
|
"example": 42,
|
|
"nullable": true,
|
|
"minimum": 0.0
|
|
}
|
|
}
|
|
},
|
|
"StreamResponse": {
|
|
"type": "object",
|
|
"required": [
|
|
"token"
|
|
],
|
|
"properties": {
|
|
"details": {
|
|
"allOf": [
|
|
{
|
|
"$ref": "#/components/schemas/StreamDetails"
|
|
}
|
|
],
|
|
"nullable": true
|
|
},
|
|
"generated_text": {
|
|
"type": "string",
|
|
"default": "null",
|
|
"example": "test",
|
|
"nullable": true
|
|
},
|
|
"token": {
|
|
"$ref": "#/components/schemas/Token"
|
|
}
|
|
}
|
|
},
|
|
"Token": {
|
|
"type": "object",
|
|
"required": [
|
|
"id",
|
|
"text",
|
|
"logprob",
|
|
"special"
|
|
],
|
|
"properties": {
|
|
"id": {
|
|
"type": "integer",
|
|
"format": "int32",
|
|
"example": 0,
|
|
"minimum": 0.0
|
|
},
|
|
"logprob": {
|
|
"type": "number",
|
|
"format": "float",
|
|
"example": -0.34,
|
|
"nullable": true
|
|
},
|
|
"special": {
|
|
"type": "boolean",
|
|
"example": "false"
|
|
},
|
|
"text": {
|
|
"type": "string",
|
|
"example": "test"
|
|
}
|
|
}
|
|
}
|
|
}
|
|
},
|
|
"tags": [
|
|
{
|
|
"name": "Text Generation Inference",
|
|
"description": "Hugging Face Text Generation Inference API"
|
|
}
|
|
]
|
|
}
|