mtmd : add support for Voxtral (#14862)

* mtmd : add support for Voxtral

* clean up

* fix python requirements

* add [BEGIN_AUDIO] token

* also support Devstral conversion

* add docs and tests

* fix regression for ultravox

* minor coding style improvement

* correct project activation fn

* Apply suggestions from code review

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

---------

Co-authored-by: Sigbjørn Skjæret <sigbjorn.skjaeret@scala.com>
This commit is contained in:
Xuan-Son Nguyen
2025-07-28 15:01:48 +02:00
committed by GitHub
parent 946b1f6859
commit 00fa15fedc
13 changed files with 546 additions and 46 deletions

View File

@@ -2724,6 +2724,7 @@ class VisionProjectorType:
INTERNVL = "internvl"
QWEN2A = "qwen2a" # audio
QWEN25O = "qwen2.5o" # omni
VOXTRAL = "voxtral"
# Items here are (block size, type size)