huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-10 20:04:52 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/main' into feat/flash_llama

Browse Source
This commit is contained in:
OlivierDehaene 2023-04-09 20:24:16 +02:00
commit a1a6b5cc20
1 changed files with 69 additions and 69 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

78
router/src/server.rs
View File

@ -87,21 +87,21 @@ async fn health(infer: Extension<Infer>) -> Result<(), (StatusCode, Json<ErrorRe
/// Generate tokens
#[utoipa::path(
post,
tag = "Text Generation Inference",
path = "/generate",
request_body = GenerateRequest,
responses(
(status = 200, description = "Generated Text", body = GenerateResponse),
(status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"})),
(status = 429, description = "Model is overloaded", body = ErrorResponse,
example = json ! ({"error": "Model is overloaded"})),
(status = 422, description = "Input validation error", body = ErrorResponse,
example = json ! ({"error": "Input validation error"})),
(status = 500, description = "Incomplete generation", body = ErrorResponse,
example = json ! ({"error": "Incomplete generation"})),
)
post,
tag = "Text Generation Inference",
path = "/generate",
request_body = GenerateRequest,
responses(
(status = 200, description = "Generated Text", body = GenerateResponse),
(status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"})),
(status = 429, description = "Model is overloaded", body = ErrorResponse,
example = json ! ({"error": "Model is overloaded"})),
(status = 422, description = "Input validation error", body = ErrorResponse,
example = json ! ({"error": "Input validation error"})),
(status = 500, description = "Incomplete generation", body = ErrorResponse,
example = json ! ({"error": "Incomplete generation"})),
)
)]
#[instrument(
skip(infer),
@ -264,26 +264,26 @@ async fn generate(
/// Generate a stream of token using Server-Sent Events
#[utoipa::path(
post,
tag = "Text Generation Inference",
path = "/generate_stream",
request_body = GenerateRequest,
responses(
(status = 200, description = "Generated Text", body = StreamResponse,
content_type = "text/event-stream"),
(status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"}),
content_type = "text/event-stream"),
(status = 429, description = "Model is overloaded", body = ErrorResponse,
example = json ! ({"error": "Model is overloaded"}),
content_type = "text/event-stream"),
(status = 422, description = "Input validation error", body = ErrorResponse,
example = json ! ({"error": "Input validation error"}),
content_type = "text/event-stream"),
(status = 500, description = "Incomplete generation", body = ErrorResponse,
example = json ! ({"error": "Incomplete generation"}),
content_type = "text/event-stream"),
)
post,
tag = "Text Generation Inference",
path = "/generate_stream",
request_body = GenerateRequest,
responses(
(status = 200, description = "Generated Text", body = StreamResponse,
content_type = "text/event-stream"),
(status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"}),
content_type = "text/event-stream"),
(status = 429, description = "Model is overloaded", body = ErrorResponse,
example = json ! ({"error": "Model is overloaded"}),
content_type = "text/event-stream"),
(status = 422, description = "Input validation error", body = ErrorResponse,
example = json ! ({"error": "Input validation error"}),
content_type = "text/event-stream"),
(status = 500, description = "Incomplete generation", body = ErrorResponse,
example = json ! ({"error": "Incomplete generation"}),
content_type = "text/event-stream"),
)
)]
#[instrument(
skip(infer),
@ -447,10 +447,10 @@ async fn generate_stream(
/// Prometheus metrics scrape endpoint
#[utoipa::path(
get,
tag = "Text Generation Inference",
path = "/metrics",
responses((status = 200, description = "Prometheus Metrics", body = String))
get,
tag = "Text Generation Inference",
path = "/metrics",
responses((status = 200, description = "Prometheus Metrics", body = String))
)]
async fn metrics(prom_handle: Extension<PrometheusHandle>) -> String {
prom_handle.render()