biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Voxtral Realtime] Change name (#33716)

Browse Source 
Signed-off-by: Patrick von Platen <patrick.v.platen@gmail.com>
This commit is contained in:
Patrick von Platen
2026-02-03 22:03:28 +01:00
committed by GitHub
parent a372f3f40a
commit 3f7662d650
4 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
examples/online_serving/openai_realtime_client.py
View File

@@ -7,7 +7,7 @@ audio transcription by uploading an audio file.
Before running this script, you must start the vLLM server with a realtime-capable
model, for example:
vllm serve mistralai/Voxtral-Mini-3B-Realtime-2602 --enforce-eager
vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --enforce-eager
Requirements:
- vllm with audio support
@@ -126,7 +126,7 @@ if __name__ == "__main__":
parser.add_argument(
"--model",
type=str,
default="mistralai/Voxtral-Mini-3B-Realtime-2602",
default="mistralai/Voxtral-Mini-4B-Realtime-2602",
help="Model that is served and should be pinged.",
)
parser.add_argument(

4
examples/online_serving/openai_realtime_microphone_client.py
View File

@@ -5,7 +5,7 @@ Minimal Gradio demo for real-time speech transcription using the vLLM Realtime A
Start the vLLM server first:
vllm serve mistralai/Voxtral-Mini-3B-Realtime-2602 --enforce-eager
vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --enforce-eager
Then run this script:
@@ -166,7 +166,7 @@ if __name__ == "__main__":
parser.add_argument(
"--model",
type=str,
default="mistralai/Voxtral-Mini-3B-Realtime-2602",
default="mistralai/Voxtral-Mini-4B-Realtime-2602",
help="Model that is served and should be pinged.",
)
parser.add_argument(

2
tests/entrypoints/openai/test_realtime_validation.py
View File

@@ -24,7 +24,7 @@ MISTRAL_FORMAT_ARGS = [
"mistral",
]
MODEL_NAME = "mistralai/Voxtral-Mini-3B-Realtime-2602"
MODEL_NAME = "mistralai/Voxtral-Mini-4B-Realtime-2602"
def _audio_to_base64_pcm16(path: str, target_sr: int = 16000) -> str:

2
tests/models/multimodal/generation/test_voxtral_realtime.py
View File

@@ -19,7 +19,7 @@ from vllm.engine.arg_utils import AsyncEngineArgs
from vllm.inputs.data import TokensPrompt
from vllm.v1.engine.async_llm import AsyncLLM, StreamingInput
MODEL_NAME = "mistralai/Voxtral-Mini-3B-Realtime-2602"
MODEL_NAME = "mistralai/Voxtral-Mini-4B-Realtime-2602"
ENGINE_CONFIG = dict(
model=MODEL_NAME,
max_model_len=8192,