huggingface/text-generation-inference
5
0
Fork 0
mirror of https://github.com/huggingface/text-generation-inference.git synced 2025-06-19 15:52:08 +00:00
Code Issues Packages Projects Releases Wiki Activity

Merge f384e0f308 into 0627983c17

Browse Source
This commit is contained in:
Wang, Yi 2025-06-17 14:14:27 +02:00 committed by GitHub
commit b4d9abec6c
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
2 changed files with 24 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
router/src/config.rs
View File

@ -265,6 +265,10 @@ impl Idefics3 {
pub fn get_max_longest_edge_for_image_resize(&self) -> usize {
1456
}
pub fn get_max_image_size(&self) -> usize {
4096
}
}
#[derive(Clone, Debug, Serialize, Deserialize)]

26
router/src/validation.rs
View File

@ -646,11 +646,10 @@ fn image_tokens(
const GLOBAL_IMG: &str = "<global-img>";
let max_longest_edge_for_image_resize = config.get_max_longest_edge_for_image_resize();
let max_image_size = config.get_max_image_size();
// resize image if it is larger than max_longest_edge_for_image_resize keeping aspect ratio
let (height, width) = if height > max_longest_edge_for_image_resize
|| width > max_longest_edge_for_image_resize
{
// resize image to max_longest_edge_for_image_resize and keep aspect ratio
let (height, width) = {
let aspect_ratio = height as f32 / width as f32;
if height > width {
(
@ -663,8 +662,23 @@ fn image_tokens(
max_longest_edge_for_image_resize,
)
}
} else {
(height, width)
};
let (height, width) = {
let aspect_ratio = height as f32 / width as f32;
if height >= width && height > max_image_size {
(
max_image_size,
(max_image_size as f32 / aspect_ratio) as usize,
)
} else if width > height && width > max_image_size {
(
(max_image_size as f32 * aspect_ratio) as usize,
max_image_size,
)
} else {
(height, width)
}
};
let image_seq_len = config.get_number_of_features();