From bfcfee7867f1229e922c9c46c471c25fa7711c9d Mon Sep 17 00:00:00 2001 From: rein yang <73573651+R2-Y@users.noreply.github.com> Date: Sat, 28 Feb 2026 10:42:50 +0800 Subject: [PATCH] [Docs] update async chunk docs diagram [skip ci] (#1530) Signed-off-by: Rein Yang --- docs/.nav.yml | 2 ++ docs/api/README.md | 2 ++ docs/design/feature/async_chunk_design.md | 4 ++-- 3 files changed, 6 insertions(+), 2 deletions(-) diff --git a/docs/.nav.yml b/docs/.nav.yml index c504478a5..d90c7e29a 100644 --- a/docs/.nav.yml +++ b/docs/.nav.yml @@ -16,6 +16,7 @@ nav: - GLM-Image Multistage End-to-End Inference: user_guide/examples/offline_inference/glm_image.md - Image-To-Image: user_guide/examples/offline_inference/image_to_image.md - Image-To-Video: user_guide/examples/offline_inference/image_to_video.md + - MiMo-Audio Offline Inference: user_guide/examples/offline_inference/mimo_audio.md - Qwen2.5-Omni: user_guide/examples/offline_inference/qwen2_5_omni.md - Qwen3-Omni: user_guide/examples/offline_inference/qwen3_omni.md - Qwen3-TTS: user_guide/examples/offline_inference/qwen3_tts.md @@ -27,6 +28,7 @@ nav: - GLM-Image Online Serving: user_guide/examples/online_serving/glm_image.md - Image-To-Image: user_guide/examples/online_serving/image_to_image.md - Image-To-Video: user_guide/examples/online_serving/image_to_video.md + - Online serving Example of vLLM-Omni for MiMo-Audio: user_guide/examples/online_serving/mimo_audio.md - Qwen2.5-Omni: user_guide/examples/online_serving/qwen2_5_omni.md - Qwen3-Omni: user_guide/examples/online_serving/qwen3_omni.md - Qwen3-TTS: user_guide/examples/online_serving/qwen3_tts.md diff --git a/docs/api/README.md b/docs/api/README.md index caa116b0e..1b90b022c 100644 --- a/docs/api/README.md +++ b/docs/api/README.md @@ -78,6 +78,8 @@ Configuration classes. - [vllm_omni.diffusion.cache.teacache.config.TeaCacheConfig][] - [vllm_omni.distributed.omni_connectors.utils.config.ConnectorSpec][] - [vllm_omni.distributed.omni_connectors.utils.config.OmniTransferConfig][] +- [vllm_omni.model_executor.models.mimo_audio.config_mimo_audio.MiMoAudioConfig][] +- [vllm_omni.model_executor.models.mimo_audio.config_mimo_audio.MiMoAudioTokenizerConfig][] - [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSConfig][] - [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSSpeakerEncoderConfig][] - [vllm_omni.model_executor.models.qwen3_tts.configuration_qwen3_tts.Qwen3TTSTalkerCodePredictorConfig][] diff --git a/docs/design/feature/async_chunk_design.md b/docs/design/feature/async_chunk_design.md index 2aedbfaff..b6a673a90 100644 --- a/docs/design/feature/async_chunk_design.md +++ b/docs/design/feature/async_chunk_design.md @@ -62,8 +62,8 @@ Enabling **async_chunk** (False→True) sharply reduces time-to-first-audio (TTF

- - TTFP Performance Data Comparison + + RTF Performance Data Comparison