model : support vision LiquidAI LFM2-VL family (#15347)

* wip lfm2 vision model

* Fix conv weight

* Implement dynamic resolution

* Fix cuda

* support LFM2-VL-450M

* happy CI

* Remove extra `ggml_conv` and put others into the right place

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>

---------

Co-authored-by: Xuan Son Nguyen <son@huggingface.co>
Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Tarek Dakhran
2025-08-16 23:33:54 +02:00
committed by GitHub
parent 1fe00296f5
commit 65349f26f2
5 changed files with 171 additions and 3 deletions

View File

@@ -2832,6 +2832,7 @@ class VisionProjectorType:
QWEN2A = "qwen2a" # audio
QWEN25O = "qwen2.5o" # omni
VOXTRAL = "voxtral"
LFM2 = "lfm2"
# Items here are (block size, type size)