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

[Doc] update diffusion_acceleration.md & FAQ memory troubleshooting (#406)

Browse Source 
Signed-off-by: David Chen <530634352@qq.com>
This commit is contained in:
WeiQing Chen authored and GitHub committed 2025-12-23 15:09:25 +08:00
1 parent 74c142460d
commit d9faeb29c0
6 files changed
+67 -11
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/acceleration/parallelism_acceleration.md
+16 -4
View File
@@ -11,12 +11,24 @@ The following parallelism methods are currently supported in vLLM-Omni:
The following table shows which models are currently supported by parallelism method:
### ImageGen
| Model | Model Identifier | Ulysses-SP |
|-------|-----------------|-----------|
| **Qwen-Image** | `Qwen/Qwen-Image` | ✅ |
| **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ❌ |
| Model | Model Identifier | Ulysses-SP |
|-------|------------------|-----------|
| **LongCat-Image** | `meituan-longcat/LongCat-Image` | ❌ |
| **LongCat-Image-Edit** | `meituan-longcat/LongCat-Image-Edit` | ❌ |
| **Ovis-Image** | `OvisAI/Ovis-Image` | ❌ |
| **Qwen-Image** | `Qwen/Qwen-Image` | ✅ |
| **Qwen-Image-Edit** | `Qwen/Qwen-Image-Edit` | ✅ |
| **Qwen-Image-Edit-2509** | `Qwen/Qwen-Image-Edit-2509` | ✅ |
| **Qwen-Image-Layered** | `Qwen/Qwen-Image-Layered` | ✅ |
| **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ❌ |
### VideoGen
| Model | Model Identifier | Ulysses-SP |
|-------|------------------|-----------|
| **Wan2.2** | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | ❌ |
### Sequence Parallelism
docs/user_guide/acceleration/teacache.md
+7 -1
View File
@@ -97,6 +97,8 @@ cache_config={"rel_l1_thresh": 0.1} # More conservative caching
## Supported Models
### ImageGen
<style>
th {
white-space: nowrap;
@@ -108,7 +110,11 @@ th {
|--------------|--------|-------------------|
| `QwenImagePipeline` | Qwen-Image | `Qwen/Qwen-Image` |
| `QwenImageEditPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit` |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit | `Qwen/Qwen-Image-Edit-2509` |
| `QwenImageEditPlusPipeline` | Qwen-Image-Edit-2509 | `Qwen/Qwen-Image-Edit-2509` |
### VideoGen
No VideoGen models are supported by TeaCache yet.
### Coming Soon
docs/user_guide/diffusion_acceleration.md
+15 -4
View File
@@ -31,13 +31,24 @@ vLLM-Omni also supports the sequence parallelism (SP) for the diffusion model, t
The following table shows which models are currently supported by each acceleration method:
### ImageGen
| Model | Model Identifier | TeaCache | Cache-DiT | Ulysses-SP |
|-------|-----------------|----------|-----------|-----------|
|-------|------------------|----------|-----------|-----------|
| **LongCat-Image** | `meituan-longcat/LongCat-Image` | ❌ | ✅ | ❌ |
| **LongCat-Image-Edit** | `meituan-longcat/LongCat-Image-Edit` | ❌ | ✅ | ❌ |
| **Ovis-Image** | `OvisAI/Ovis-Image` | ❌ | ✅ | ❌ |
| **Qwen-Image** | `Qwen/Qwen-Image` | ✅ | ✅ | ✅ |
| **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ❌ | ✅ |❌ |
| **Qwen-Image-Edit** | `Qwen/Qwen-Image-Edit` | ✅ | ✅ |✅ |
| **Qwen-Image-Edit-2509** | `Qwen/Qwen-Image-Edit-2509` | ❌ | ✅ |✅ |
| **Qwen-Image-Edit** | `Qwen/Qwen-Image-Edit` | ✅ | ✅ | ✅ |
| **Qwen-Image-Edit-2509** | `Qwen/Qwen-Image-Edit-2509` | ✅ | ✅ | ✅ |
| **Qwen-Image-Layered** | `Qwen/Qwen-Image-Layered` | ❌ | ✅ | ✅ |
| **Z-Image** | `Tongyi-MAI/Z-Image-Turbo` | ❌ | ✅ | ❌ |
### VideoGen
| Model | Model Identifier | TeaCache | Cache-DiT | Ulysses-SP |
|-------|------------------|----------|-----------|-----------|
| **Wan2.2** | `Wan-AI/Wan2.2-T2V-A14B-Diffusers` | ❌ | ✅ | ❌ |
## Performance Benchmarks