Skip to content

AWS releases vLLM-Omni multimodal tutorial on SageMaker

2 reports 1 reporting sources first reported Updated 2026-09-29

Understand the event

Report summary

AWS released a tutorial demonstrating how to deploy Qwen3-TTS on Amazon SageMaker AI using the vLLM-Omni DLC, streaming text in and 24 kHz PCM audio chunks out via SageMaker bidirectional streaming, with a Gradio app for trying it out.

From AWS Machine Learning Blog

Read next

More changes in today’s briefingGemini Connects to Google Wallet for Personal Finance Insights

Report timeline

Follow the reports to explore different sides of the event.

9/29
  1. Build a real-time voice app with vLLM-Omni on SageMaker AI (Part 1)

    An AWS tutorial shows how to deploy Qwen3-TTS on Amazon SageMaker AI using the vLLM-Omni DLC. A bidirectional SageMaker streaming connection sends text in and streams 24 kHz PCM audio chunks out, with a Gradio app for testing.

  2. Generate images and video with vLLM-Omni on SageMaker AI (Part 2)

    An AWS tutorial shows how to deploy two endpoints using the same vLLM-Omni DLC image on SageMaker AI: a real-time endpoint using FLUX.2-klein-4B for image generation and an asynchronous endpoint using Wan2.1-VACE-1.3B for image-conditioned video generation. A text prompt first produces a PNG, then the image and motion prompt are sent through Amazon S3 to the video endpoint. The generated MP4 is retrieved from S3. The example includes a command-line workflow and an optional Streamlit interface.

Keep up with AI, one email a day

Model releases, price changes and compute developments, with original sources. Free, confirmed by email, and easy to unsubscribe. Read a past issue