[Docs] update async chunk docs diagram [skip ci] (#1530)
Signed-off-by: Rein Yang <ruiruyang2@gmail.com>
This commit is contained in:
1 parent
fe0c02ee78
commit
bfcfee7867
3 files changed
+6
-2
No files matched your search
@@ -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
|
||||
|
||||
@@ -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][]
|
||||
|
||||
@@ -62,8 +62,8 @@ Enabling **async_chunk** (False→True) sharply reduces time-to-first-audio (TTF
|
||||
|
||||
<p align="center">
|
||||
<picture>
|
||||
<source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/performance/qwen3-omni_rft_performance.png">
|
||||
<img alt="TTFP Performance Data Comparison" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/performance/qwen3-omni_rft_performance.png" width=100%>
|
||||
<source media="(prefers-color-scheme: dark)" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/performance/qwen3-omni_rtf_performance.png">
|
||||
<img alt="RTF Performance Data Comparison" src="https://raw.githubusercontent.com/vllm-project/vllm-omni/refs/heads/main/docs/source/performance/qwen3-omni_rtf_performance.png" width=100%>
|
||||
</picture>
|
||||
</p>
|
||||
|
||||
|
||||
Reference in new issue
Block a user