huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-09-09 19:34:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add header option to disable buffering for the response stream.

Browse Source
This commit is contained in:
Robert Kimball 2023-06-27 17:48:26 +00:00
parent ae466a8736
commit 83de8a5ef9
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
router/src/server.rs
View File

@ -351,6 +351,7 @@ async fn generate_stream(
"x-compute-characters",
compute_characters.to_string().parse().unwrap(),
);
headers.insert("X-Accel-Buffering", "no".parse().unwrap());
let stream = async_stream::stream! {
// Inference