[Doc] refactor diffusion doc (#753)

Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>

docs/user_guide/diffusion/cpu_offload_diffusion.md

@@ -0,0 +1,29 @@
+# CPU Offloading for Diffusion Model
+
+## Overview
+CPU offload lets the diffusion worker move large model components between GPU and CPU memory on demand. It keeps the DiT transformer resident on GPU only while it is actively running, and swaps it out when encoders modules need the device. This reduces peak VRAM usage so bigger checkpoints run on smaller GPUs, or multiple requests can share the same GPU.
+
+## Execution Model
+1. Text encoders run on GPU while the DiT transformer is offloaded to CPU.
+2. Before denoising, weights are prefetched back to GPU, honoring pinned-memory copies for speed.
+3. After the diffusion step, the transformer returns to CPU and the process repeats as needed.
+
+Transfers use pinned host buffers, and the worker coordinates swaps via mutex-style hooks so components never compete for memory.
+
+## Configuration
+You can enable CPU offload in two ways:
+
+- **Python API**: set `enable_cpu_offload=True`.
+
+```python
+from vllm_omni import Omni
+
+if __name__ == "__main__":
+
+    m = Omni(model="Qwen/Qwen-Image",enable_cpu_offload=True)
+```
+
+- **CLI**: pass `--enable-cpu-offload` to the diffusion service entrypoint.
+
+## Known Limitations
+- Cold start latency increases for over one minute for some models(e.g., Qwen-Image)

docs/user_guide/diffusion_acceleration.md

@@ -6,8 +6,8 @@ vLLM-Omni supports various cache acceleration methods to speed up diffusion mode
 
 vLLM-Omni currently supports two main cache acceleration backends:
 
-1. **[TeaCache](acceleration/teacache.md)** - Hook-based adaptive caching that caches transformer computations when consecutive timesteps are similar
-2. **[Cache-DiT](acceleration/cache_dit_acceleration.md)** - Library-based acceleration using multiple techniques:
+1. **[TeaCache](diffusion/teacache.md)** - Hook-based adaptive caching that caches transformer computations when consecutive timesteps are similar
+2. **[Cache-DiT](diffusion/cache_dit_acceleration.md)** - Library-based acceleration using multiple techniques:
     - **DBCache** (Dual Block Cache): Caches intermediate transformer block outputs based on residual differences
     - **TaylorSeer**: Uses Taylor expansion-based forecasting for faster inference
     - **SCM** (Step Computation Masking): Selectively computes steps based on adaptive masking
@@ -16,11 +16,11 @@ Both methods can provide significant speedups (typically **1.5x-2.0x**) while ma
 
 vLLM-Omni also supports parallelism methods for diffusion models, including:
 
-1. [Ulysses-SP](acceleration/parallelism_acceleration.md#ulysses-sp) - splits the input along the sequence dimension and uses all-to-all communication to allow each device to compute only a subset of attention heads.
+1. [Ulysses-SP](diffusion/parallelism_acceleration.md#ulysses-sp) - splits the input along the sequence dimension and uses all-to-all communication to allow each device to compute only a subset of attention heads.
 
-2. [Ring-Attention](acceleration/parallelism_acceleration.md#ring-attention) - splits the input along the sequence dimension and uses ring-based P2P communication to accumulate attention results, keeping the sequence dimension sharded.
+2. [Ring-Attention](diffusion/parallelism_acceleration.md#ring-attention) - splits the input along the sequence dimension and uses ring-based P2P communication to accumulate attention results, keeping the sequence dimension sharded.
 
-3. [CFG-Parallel](acceleration/parallelism_acceleration.md#cfg-parallel) - runs the positive/negative prompts of classifier-free guidance (CFG) on different devices, then merges on a single device to perform the scheduler step.
+3. [CFG-Parallel](diffusion/parallelism_acceleration.md#cfg-parallel) - runs the positive/negative prompts of classifier-free guidance (CFG) on different devices, then merges on a single device to perform the scheduler step.
 
 ## Quick Comparison
 
@@ -197,7 +197,7 @@ outputs = omni.generate(prompt="turn this cat to a dog",
 
 For detailed information on each acceleration method:
 
-- **[TeaCache Guide](acceleration/teacache.md)** - Complete TeaCache documentation, configuration options, and best practices
-- **[Cache-DiT Acceleration Guide](acceleration/cache_dit_acceleration.md)** - Comprehensive Cache-DiT guide covering DBCache, TaylorSeer, SCM, and configuration parameters
-- **[Sequence Parallelism](acceleration/parallelism_acceleration.md#sequence-parallelism)** - Guidance on how to set sequence parallelism with configuration.
-- **[CFG-Parallel](acceleration/parallelism_acceleration.md#cfg-parallel)** - Guidance on how to set CFG-Parallel to run positive/negative branches across ranks.
+- **[TeaCache Guide](diffusion/teacache.md)** - Complete TeaCache documentation, configuration options, and best practices
+- **[Cache-DiT Acceleration Guide](diffusion/cache_dit_acceleration.md)** - Comprehensive Cache-DiT guide covering DBCache, TaylorSeer, SCM, and configuration parameters
+- **[Sequence Parallelism](diffusion/parallelism_acceleration.md#sequence-parallelism)** - Guidance on how to set sequence parallelism with configuration.
+- **[CFG-Parallel](diffusion/parallelism_acceleration.md#cfg-parallel)** - Guidance on how to set CFG-Parallel to run positive/negative branches across ranks.