anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[feature] stable_audio_open_1 teacache support (#1314)

Browse Source 
Signed-off-by: akshatvishu <akshatnayak197@gmail.com>
This commit is contained in:
akshatvishu authored and GitHub committed 2026-03-24 01:00:45 -04:00
1 parent d71c9ae60f
commit ad5e4e5710
4 files changed
+162 -9
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/diffusion_acceleration.md
+6
View File
@@ -93,6 +93,12 @@ The following table shows which models are currently supported by each accelerat
| **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ✅ | ✅ |
### AudioGen
| Model | Model Identifier | TeaCache | Cache-DiT | Ulysses-SP | Ring-Attention | CFG-Parallel |
|------------------------|------------------------------------------|:--------:|:---------:|:----------:|:--------------:|:------------:|
| **Stable-Audio-Open** | `stabilityai/stable-audio-open-1.0` | ✅ | | | | |
## Performance Benchmarks
The following benchmarks were measured on **Qwen/Qwen-Image** and **Qwen/Qwen-Image-Edit** models generating 1024x1024 images with 50 inference steps: