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

[Core][Frontend] Support request-level batching for diffusion pipelines (#4079)

Browse Source 
Signed-off-by: jader <yjader@foxmail.com>
Co-authored-by: Samit <285365963@qq.com>
This commit is contained in:
JiangJie ZhangandSamit authored and GitHub committed 2026-06-29 18:09:19 +02:00
1 parent 504698dec8
commit c45ac74d43
123 files changed
+4160 -2233
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/diffusion_features.md
+6 -2
View File
@@ -75,13 +75,17 @@ Extension methods add specialized capabilities to diffusion models beyond standa
### Execution Modes
Execution modes control how the diffusion pipeline processes denoise steps.
Execution modes control how the diffusion pipeline processes requests and
denoise steps.
| Method | Description | Best For |
|--------|-------------|----------|
| **[Request-Level Batching](diffusion/request_batching.md)** | Scheduler batches compatible independent diffusion requests into one pipeline forward pass | Bursty online serving and multi-request throughput |
| **[Step Execution](diffusion/step_execution.md)** | Per-step denoise execution with mid-request abort support | Request cancellation between denoise steps, fine-grained execution control |
**Note:** Step execution is currently supported by QwenImagePipeline only. See [Supported Models](#supported-models) for details.
**Note:** Request-level batching is available for pipelines that declare the
request-batch forward contract. Step execution is currently supported by
QwenImagePipeline only. See [Supported Models](#supported-models) for details.
### Quantization Methods