mirror of
https://github.com/huggingface/text-generation-inference.git
synced 2025-04-21 23:12:07 +00:00
router: send the input as chunks to the backend
Before this change, the generation input was sent to the backend as a single string, encoding images as Base64 and packing them in Markdown-style links. This change adds a new chunked input representation that separates text chunks from images chunks. Image chunks contain binary data (for smaller message sizes) and the image's MIME type. The stringly-typed inputs are still sent to support backends that do not support chunked inputs yet.
This commit is contained in:
parent
fc52ba61ab
commit
ebeea9daf8
@ -714,7 +714,7 @@ pub enum ValidationError {
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use crate::config::{Idefics2, LlavaNext, PaliTextConfig, Paligemma, TextConfig, VisionConfig};
|
||||
use crate::config::{PaliTextConfig, Paligemma};
|
||||
use crate::default_parameters;
|
||||
use crate::tests::get_tokenizer;
|
||||
|
||||
|
Loading…
Reference in New Issue
Block a user