Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

v0.3.0 (#72)

This commit is contained in:
OlivierDehaene 2023-02-16 17:28:29 +01:00 committed by GitHub
parent 439fcaf810
commit c720555adc
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
7 changed files with 48 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
Cargo.lock generated
View File

@ -785,7 +785,7 @@ checksum = "d2fabcfbdc87f4758337ca535fb41a6d701b65693ce38287d856d1674551ec9b"
[[package]] [[package]]
name = "grpc-metadata" name = "grpc-metadata"
version = "0.1.0" version = "0.3.0"
dependencies = [ dependencies = [
"opentelemetry", "opentelemetry",
"tonic", "tonic",
@ -2222,7 +2222,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-client" name = "text-generation-client"
version = "0.2.1" version = "0.3.0"
dependencies = [ dependencies = [
"futures", "futures",
"grpc-metadata", "grpc-metadata",
@ -2239,7 +2239,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-launcher" name = "text-generation-launcher"
version = "0.2.1" version = "0.3.0"
dependencies = [ dependencies = [
"clap 4.1.4", "clap 4.1.4",
"ctrlc", "ctrlc",
@ -2254,7 +2254,7 @@ dependencies = [
[[package]] [[package]]
name = "text-generation-router" name = "text-generation-router"
version = "0.2.1" version = "0.3.0"
dependencies = [ dependencies = [
"async-stream", "async-stream",
"axum", "axum",

85
docs/openapi.json
View File

@ -11,7 +11,7 @@
"name": "Apache 2.0", "name": "Apache 2.0",
"url": "https://www.apache.org/licenses/LICENSE-2.0" "url": "https://www.apache.org/licenses/LICENSE-2.0"
}, },
"version": "0.2.1" "version": "0.3.0"
}, },
"paths": { "paths": {
"/generate": { "/generate": {
@ -38,10 +38,7 @@
"content": { "content": {
"application/json": { "application/json": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/GenerateResponse"
"items": {
"$ref": "#/components/schemas/GenerateResponse"
}
} }
} }
} }
@ -51,10 +48,7 @@
"content": { "content": {
"application/json": { "application/json": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Input validation error" "error": "Input validation error"
@ -67,10 +61,7 @@
"content": { "content": {
"application/json": { "application/json": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Request failed during generation" "error": "Request failed during generation"
@ -83,10 +74,7 @@
"content": { "content": {
"application/json": { "application/json": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Model is overloaded" "error": "Model is overloaded"
@ -99,10 +87,7 @@
"content": { "content": {
"application/json": { "application/json": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Incomplete generation" "error": "Incomplete generation"
@ -136,12 +121,9 @@
"200": { "200": {
"description": "Generated Text", "description": "Generated Text",
"content": { "content": {
"text/event-stream ": { "text/event-stream": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/StreamResponse"
"items": {
"$ref": "#/components/schemas/StreamResponse"
}
} }
} }
} }
@ -149,12 +131,9 @@
"422": { "422": {
"description": "Input validation error", "description": "Input validation error",
"content": { "content": {
"text/event-stream ": { "text/event-stream": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Input validation error" "error": "Input validation error"
@ -165,12 +144,9 @@
"424": { "424": {
"description": "Generation Error", "description": "Generation Error",
"content": { "content": {
"text/event-stream ": { "text/event-stream": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Request failed during generation" "error": "Request failed during generation"
@ -181,12 +157,9 @@
"429": { "429": {
"description": "Model is overloaded", "description": "Model is overloaded",
"content": { "content": {
"text/event-stream ": { "text/event-stream": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Model is overloaded" "error": "Model is overloaded"
@ -197,12 +170,9 @@
"500": { "500": {
"description": "Incomplete generation", "description": "Incomplete generation",
"content": { "content": {
"text/event-stream ": { "text/event-stream": {
"schema": { "schema": {
"type": "array", "$ref": "#/components/schemas/ErrorResponse"
"items": {
"$ref": "#/components/schemas/ErrorResponse"
}
}, },
"example": { "example": {
"error": "Incomplete generation" "error": "Incomplete generation"
@ -213,6 +183,29 @@
}, },
"deprecated": false "deprecated": false
} }
},
"/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"
}
}
}
}
},
"deprecated": false
}
} }
}, },
"components": { "components": {

2
launcher/Cargo.toml
View File

@ -1,6 +1,6 @@
[package] [package]
name = "text-generation-launcher" name = "text-generation-launcher"
version = "0.2.1" version = "0.3.0"
edition = "2021" edition = "2021"
authors = ["Olivier Dehaene"] authors = ["Olivier Dehaene"]
description = "Text Generation Launcher" description = "Text Generation Launcher"

2
router/Cargo.toml
View File

@ -1,6 +1,6 @@
[package] [package]
name = "text-generation-router" name = "text-generation-router"
version = "0.2.1" version = "0.3.0"
edition = "2021" edition = "2021"
authors = ["Olivier Dehaene"] authors = ["Olivier Dehaene"]
description = "Text Generation Webserver" description = "Text Generation Webserver"

2
router/client/Cargo.toml
View File

@ -1,6 +1,6 @@
[package] [package]
name = "text-generation-client" name = "text-generation-client"
version = "0.2.1" version = "0.3.0"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

2
router/grpc-metadata/Cargo.toml
View File

@ -1,6 +1,6 @@
[package] [package]
name = "grpc-metadata" name = "grpc-metadata"
version = "0.1.0" version = "0.3.0"
edition = "2021" edition = "2021"
[dependencies] [dependencies]

2
server/pyproject.toml
View File

@ -1,6 +1,6 @@
[tool.poetry] [tool.poetry]
name = "text-generation" name = "text-generation"
version = "0.2.1" version = "0.3.0"
description = "Text Generation Inference Python gRPC Server" description = "Text Generation Inference Python gRPC Server"
authors = ["Olivier Dehaene <olivier@huggingface.co>"] authors = ["Olivier Dehaene <olivier@huggingface.co>"]