xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-01-26 03:44:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

Remove audio optional dependency for mistral-common (#28722)

Browse Source 
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
This commit is contained in:
Julien Denize 2025-11-14 18:54:38 +01:00 committed by GitHub
parent a17e36f223
commit 085424808e
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
4 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
docs/contributing/model/transcription.md
View File

@ -249,7 +249,7 @@ No extra registration is required beyond having your model class available via t
## Examples in-tree
- Whisper encoder–decoder (audio-only): [vllm/model_executor/models/whisper.py](../../../vllm/model_executor/models/whisper.py)
- Voxtral decoder-only (audio embeddings + LLM): [vllm/model_executor/models/voxtral.py](../../../vllm/model_executor/models/voxtral.py)
- Voxtral decoder-only (audio embeddings + LLM): [vllm/model_executor/models/voxtral.py](../../../vllm/model_executor/models/voxtral.py). Make sure to have installed `mistral-common[audio]`.
- Gemma3n decoder-only with fixed instruction prompt: [vllm/model_executor/models/gemma3n_mm.py](../../../vllm/model_executor/models/gemma3n_mm.py)
## Test with the API

3
docs/models/supported_models.md
View File

@ -785,6 +785,9 @@ Speech2Text models trained specifically for Automatic Speech Recognition.
| `Gemma3nForConditionalGeneration` | Gemma3n | `google/gemma-3n-E2B-it`, `google/gemma-3n-E4B-it`, etc. | | |
| `GraniteSpeechForConditionalGeneration` | Granite Speech | `ibm-granite/granite-speech-3.3-2b`, `ibm-granite/granite-speech-3.3-8b`, etc. | ✅︎ | ✅︎ |
!!! note
`VoxtralForConditionalGeneration` requires `mistral-common[audio]` to be installed.
### Pooling Models
See [this page](./pooling_models.md) for more information on how to use pooling models.

1
examples/offline_inference/audio_language.py
View File

@ -43,6 +43,7 @@ class ModelRequestData(NamedTuple):
# Voxtral
# Make sure to install mistral-common[audio].
def run_voxtral(question: str, audio_count: int) -> ModelRequestData:
from mistral_common.audio import Audio
from mistral_common.protocol.instruct.chunk import (

2
requirements/common.txt
View File

@ -31,7 +31,7 @@ partial-json-parser # used for parsing partial JSON outputs
pyzmq >= 25.0.0
msgspec
gguf >= 0.13.0
mistral_common[image,audio] >= 1.8.5
mistral_common[image] >= 1.8.5
opencv-python-headless >= 4.11.0 # required for video IO
pyyaml
six>=1.16.0; python_version > '3.11' # transitive dependency of pandas that needs to be the latest version for python 3.12