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

[Diffusion] Add VAE patch parallel support for FLUX.2-dev (#5292)

Browse Source 
Signed-off-by: dpeng123 <diyapeng123@gmail.com>
This commit is contained in:
Diya Peng authored and GitHub committed 2026-07-24 07:00:57 +00:00
1 parent 6eed6b9434
commit acf941da4d
6 files changed
+349 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/design/feature/vae_parallel.md
+1
View File
@@ -445,6 +445,7 @@ Complete examples in the codebase:
| **Z-Image** | `vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl.py` | ✅ | ❌ |
| **Wan2.2** | `vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_wan.py` | ✅ | ✅ |
| **Qwen-Image** | `vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_qwenimage.py` | ✅ | ❌ |
| **FLUX.2-dev** | `vllm_omni/diffusion/distributed/autoencoders/autoencoder_kl_flux2.py` | ✅ | ✅ |
---
docs/user_guide/diffusion_features.md
+1 -1
View File
@@ -117,7 +117,7 @@ The following tables show which models support each feature:
| **FLUX.1-schnell** | ❌ | ✅ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ |
| **FLUX.2-klein** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ |
| **FLUX.1-Kontext-dev** | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| **FLUX.2-dev** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ❌ | ❌ | ❌ |
| **FLUX.2-dev** | ✅ | ✅ | ✅ | ✅ | ✅ | ❌ | ✅ | ✅ | ✅ | ❌ | ❌ |
| **GLM-Image** | ❌ | ❌ | ❌ | ✅ | ✅ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ |
| **Hidream-I1-Full** | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ❌ | ❌ |
| **HunyuanImage3** | ❌ | ✅ | ❌ | ❌ | ✅ | ❌ | ❌ | ❌ | ❌ | ✅ | ❌ |