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

[Feature] Add support for Pipeline Parallel and integrate it into Wan 2.2 (#2322)

Browse Source 
Signed-off-by: Rustam Khadipash <16683750+hadipash@users.noreply.github.com>
This commit is contained in:
Rustam Khadipash authored and GitHub committed 2026-05-19 09:42:17 +08:00
1 parent 475a4002b0
commit 89f8819525
20 files changed
+1981 -1009
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

docs/user_guide/diffusion/parallelism/overview.md
+9 -8
View File
@@ -4,13 +4,14 @@ This guide covers the parallelism methods in vLLM-Omni for speeding up diffusion
## Supported Methods
| Method | Description |
|--------|-------------|
| **[Tensor Parallelism](tensor_parallel.md)** | Shards DiT weights across GPUs to reduce per-GPU memory |
| **[Sequence Parallelism](sequence_parallel.md)** | Splits sequence dimension across GPUs (Ulysses-SP, Ring-Attention, or hybrid) for high-resolution images and videos |
| **[CFG-Parallel](cfg_parallel.md)** | Runs CFG positive/negative branches on separate GPUs for ~1.8x speedup on guided generation |
| **[VAE Patch Parallelism](vae_patch_parallel.md)** | Distributes VAE decode spatially across GPUs to reduce peak VAE memory |
| **[HSDP](hsdp.md)** | Shards full model weights via PyTorch FSDP2 to enable large-model inference on memory-constrained GPUs |
| **[Expert Parallelism](expert_parallel.md)** | Shards MoE expert blocks across GPUs for MoE models (e.g. HunyuanImage3.0) |
| Method | Description |
|----------------------------------------------------|---------------------------------------------------------------------------------------------------------------------|
| **[Tensor Parallelism](tensor_parallel.md)** | Shards DiT weights across GPUs to reduce per-GPU memory |
| **[Sequence Parallelism](sequence_parallel.md)** | Splits sequence dimension across GPUs (Ulysses-SP, Ring-Attention, or hybrid) for high-resolution images and videos |
| **[CFG-Parallel](cfg_parallel.md)** | Runs CFG positive/negative branches on separate GPUs for ~1.8x speedup on guided generation |
| **[Pipeline Parallelism](pipeline_parallel.md)** | Splits the denoising transformer block-wise across sequential GPU stages to reduce per-GPU model memory |
| **[VAE Patch Parallelism](vae_patch_parallel.md)** | Distributes VAE decode spatially across GPUs to reduce peak VAE memory |
| **[HSDP](hsdp.md)** | Shards full model weights via PyTorch FSDP2 to enable large-model inference on memory-constrained GPUs |
| **[Expert Parallelism](expert_parallel.md)** | Shards MoE expert blocks across GPUs for MoE models (e.g. HunyuanImage3.0) |
See [Supported Models](../../diffusion_features.md#supported-models) for per-model compatibility.