huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-11 12:24:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix: adjust rebase removals

Browse Source
This commit is contained in:
drbh 2024-04-16 22:42:58 +00:00
parent 4fec982325
commit 593c443b45
2 changed files with 10 additions and 16 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
router/src/lib.rs
View File

@ -959,20 +959,6 @@ pub(crate) struct Details {
pub top_tokens: Vec<Vec<Token>>, pub top_tokens: Vec<Vec<Token>>,
} }
impl Default for Details {
fn default() -> Self {
Self {
finish_reason: FinishReason::Length,
generated_tokens: 0,
seed: None,
prefill: Vec::new(),
tokens: Vec::new(),
best_of_sequences: None,
top_tokens: Vec::new(),
}
}
}
#[derive(Serialize, ToSchema)] #[derive(Serialize, ToSchema)]
pub(crate) struct GenerateResponse { pub(crate) struct GenerateResponse {
#[schema(example = "test")] #[schema(example = "test")]

12
router/src/server.rs
View File

@ -551,7 +551,11 @@ async fn generate_stream_internal(
path = "/v1/completions", path = "/v1/completions",
request_body = CompletionRequest, request_body = CompletionRequest,
responses( responses(
(status = 200, description = "Generated Text", body = ChatCompletionChunk), (status = 200, description = "Generated Chat Completion",
content(
("application/json" = Completion),
("text/event-stream" = CompletionCompleteChunk),
)),
(status = 424, description = "Generation Error", body = ErrorResponse, (status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"})), example = json ! ({"error": "Request failed during generation"})),
(status = 429, description = "Model is overloaded", body = ErrorResponse, (status = 429, description = "Model is overloaded", body = ErrorResponse,
@ -934,7 +938,11 @@ async fn completions(
path = "/v1/chat/completions", path = "/v1/chat/completions",
request_body = ChatRequest, request_body = ChatRequest,
responses( responses(
(status = 200, description = "Generated Text", body = ChatCompletionChunk), (status = 200, description = "Generated Chat Completion",
content(
("application/json" = ChatCompletion),
("text/event-stream" = ChatCompletionChunk),
)),
(status = 424, description = "Generation Error", body = ErrorResponse, (status = 424, description = "Generation Error", body = ErrorResponse,
example = json ! ({"error": "Request failed during generation"})), example = json ! ({"error": "Request failed during generation"})),
(status = 429, description = "Model is overloaded", body = ErrorResponse, (status = 429, description = "Model is overloaded", body = ErrorResponse,