huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-04-21 23:12:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

Update server.rs

Browse Source
This commit is contained in:
Merve Noyan 2023-08-21 11:08:38 +03:00 committed by GitHub
parent 09fee2f6fb
commit 6541d8d8d9
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 4 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
router/src/server.rs
View File

@ -123,17 +123,16 @@ responses(
(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"})),
example = json ! ({"error": "Model çis 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"})),
params("max_input_length" = usize, Path, description = "This is the maximum allowed input
),
params(("max_input_length" = usize, Path, description = "This is the maximum allowed input
length (expressed in number of tokens) for users. The larger this value, the longer prompt
users can send which can impact the overall memory required to handle the load.
Please note that some models have a finite range of sequence they can handle."),
),
)
Please note that some models have a finite range of sequence they can handle.")),
)]
#[instrument(
skip_all,