docs: organize offloader feature designs

Signed-off-by: Hongsheng Liu <liuhongsheng4@huawei.com>

docs/.nav.yml

@@ -138,10 +138,10 @@ nav:
           - Backend Selection: design/feature/attention_backend_selection.md
           - Skip-Softmax: design/feature/skip_softmax.md
         - CPU Offloading:
-          - Overview: design/feature/cpu_offloading.md
-          - Model-Level: design/feature/model_level_offload.md
-          - Layerwise: design/feature/layerwise_offload.md
-          - Distributed Layerwise: design/feature/distributed_layerwise_offload.md
+          - Overview: design/feature/offloader/README.md
+          - Model-Level: design/feature/offloader/cpu_offload.md
+          - Layerwise: design/feature/offloader/layerwise_offload.md
+          - Distributed Layerwise: design/feature/offloader/distributed_layerwise_offload.md
         - Cache-DiT: design/feature/cache_dit.md
         - TeaCache: design/feature/teacache.md
         - Diffusion Continuous Batching: design/feature/diffusion_continuous_batching.md

docs/design/architecture_overview.md

@@ -406,7 +406,7 @@ the source for configuration, compatibility, and implementation details.
   stage contract.
 * **Quantization and memory efficiency:** [Quantization](feature/quantization.md)
   resolves per-pipeline or per-component quantization configurations, while
-  [Distributed Layerwise Offload](feature/distributed_layerwise_offload.md)
+  [Distributed Layerwise Offload](feature/offloader/distributed_layerwise_offload.md)
   streams diffusion blocks from host memory within the existing parallel
   topology.
 

docs/design/feature/offloader/README.md

@@ -5,9 +5,9 @@ The three strategies have separate user and design pages:
 
 | Strategy | User guide | Design contract |
 | --- | --- | --- |
-| Model-level | [Guide](../../user_guide/diffusion/offloader/cpu_offload.md) | [Design](model_level_offload.md) |
-| Layerwise | [Guide](../../user_guide/diffusion/offloader/layerwise_offload.md) | [Design](layerwise_offload.md) |
-| Distributed layerwise | [Guide](../../user_guide/diffusion/offloader/distributed_layerwise_offload.md) | [Design](distributed_layerwise_offload.md) |
+| Model-level | [Guide](../../../user_guide/diffusion/offloader/cpu_offload.md) | [Design](cpu_offload.md) |
+| Layerwise | [Guide](../../../user_guide/diffusion/offloader/layerwise_offload.md) | [Design](layerwise_offload.md) |
+| Distributed layerwise | [Guide](../../../user_guide/diffusion/offloader/distributed_layerwise_offload.md) | [Design](distributed_layerwise_offload.md) |
 
 ## Strategy selection
 
@@ -76,5 +76,5 @@ ownership.
 - Platform streams, events, synchronization, and cache management go through
   the vLLM-Omni platform abstraction.
 
-The diffusion [Offloader module design](../module/diffusion/offloader.md)
+The diffusion [Offloader module design](../../module/diffusion/offloader.md)
 describes how these feature contracts fit into the larger diffusion runtime.

docs/design/feature/offloader/cpu_offload.md

@@ -2,7 +2,7 @@
 
 Model-level offload enforces mutual exclusion between pipeline component
 groups. For commands and model support, see the
-[model-level user guide](../../user_guide/diffusion/offloader/cpu_offload.md).
+[model-level user guide](../../../user_guide/diffusion/offloader/cpu_offload.md).
 
 ## Generic hook path
 
@@ -53,4 +53,4 @@ attribute-name heuristics.
   residency is restored.
 
 Shared selection and lifecycle behavior is defined in the
-[CPU Offloading design](cpu_offloading.md).
+[CPU Offloading design](README.md).

docs/design/feature/offloader/distributed_layerwise_offload.md

@@ -7,7 +7,7 @@ either shard those host-side weights across an existing parallel group or keep
 the standard loader's rank-local weights and avoid an additional collective.
 
 For user-facing commands, see the
-[distributed layerwise offloading guide](../../user_guide/diffusion/offloader/distributed_layerwise_offload.md)
+[distributed layerwise offloading guide](../../../user_guide/diffusion/offloader/distributed_layerwise_offload.md)
 and the [Cosmos3 recipe](https://github.com/vllm-project/vllm-omni/blob/main/recipes/cosmos3/Cosmos3-DistOffload.md).
 
 ## Status
@@ -56,7 +56,7 @@ AllGather:                [full N+1]             [full N+2]
 Buffers:    [current slot]       [prefetch slot]       [current slot]
 ```
 
-![DLO double-buffer prefetch pipeline](../figures/dlo/dlo_pipeline.gif)
+![DLO double-buffer prefetch pipeline](../../figures/dlo/dlo_pipeline.gif)
 
 The backend uses two shared device buffers, so accelerator weight residency is
 bounded by the largest streamed blocks rather than the complete model.

docs/design/feature/offloader/layerwise_offload.md

@@ -2,7 +2,7 @@
 
 Layerwise offload streams transformer blocks through one accelerator. For
 commands and model support, see the
-[layerwise user guide](../../user_guide/diffusion/offloader/layerwise_offload.md).
+[layerwise user guide](../../../user_guide/diffusion/offloader/layerwise_offload.md).
 
 ## Hook ring
 
@@ -54,4 +54,4 @@ streamed by this backend.
   [Distributed Layerwise Offload](distributed_layerwise_offload.md).
 
 Shared selection and lifecycle behavior is defined in the
-[CPU Offloading design](cpu_offloading.md).
+[CPU Offloading design](README.md).

docs/design/feature/quantization.md

@@ -186,7 +186,7 @@ Distributed layerwise offload has an additional boundary: its sharded mmap
 AllGather path is not compatible with online quantization because the path
 expects already materialized checkpoint weights. Use the rank-local
 `--dlo-no-use-allgather` path or a compatible pre-quantized checkpoint when
-combining these features. See the [DLO design document](distributed_layerwise_offload.md)
+combining these features. See the [DLO design document](offloader/distributed_layerwise_offload.md)
 for the full compatibility matrix.
 
 ## Adding a quantization backend

docs/design/index.md

@@ -61,10 +61,10 @@ The design contracts separate selection mechanics from backend algorithms:
 
 #### CPU offloading
 
-- [Overview and Shared Contracts](feature/cpu_offloading.md)
-- [Model-Level Offload](feature/model_level_offload.md)
-- [Layerwise Offload](feature/layerwise_offload.md)
-- [Distributed Layerwise Offload](feature/distributed_layerwise_offload.md)
+- [Overview and Shared Contracts](feature/offloader/README.md)
+- [Model-Level Offload](feature/offloader/cpu_offload.md)
+- [Layerwise Offload](feature/offloader/layerwise_offload.md)
+- [Distributed Layerwise Offload](feature/offloader/distributed_layerwise_offload.md)
 
 - [Cache-DiT](feature/cache_dit.md)
 - [TeaCache](feature/teacache.md)

docs/features/README.md

@@ -48,7 +48,7 @@ defines the shared configuration and backend extension points.
 | Goal | User guide | Related design contract |
 | --- | --- | --- |
 | Compare acceleration methods and supported combinations | [Overview](../user_guide/diffusion_features.md), [Feature Compatibility](../user_guide/feature_compatibility.md) | [Diffusion acceleration designs](../design/index.md#diffusion-acceleration) |
-| Move weights between host and device memory | [CPU Offloading](../user_guide/diffusion/cpu_offload.md) | [CPU Offloading](../design/feature/cpu_offloading.md) |
+| Move weights between host and device memory | [CPU Offloading](../user_guide/diffusion/cpu_offload.md) | [CPU Offloading](../design/feature/offloader/README.md) |
 | Reuse denoising computation | [Cache Acceleration](../user_guide/diffusion/cache_acceleration/cache_dit.md) | [Cache-DiT](../design/feature/cache_dit.md), [TeaCache](../design/feature/teacache.md) |
 | Distribute diffusion work across devices | [Parallelism](../user_guide/diffusion/parallelism/overview.md) | [Parallelism designs](../design/index.md#parallelism) |
 | Select dense, sparse, or quantized attention paths | [Attention Backends](../user_guide/diffusion/attention_backends.md) | [Attention Backend Selection](../design/feature/attention_backend_selection.md) |

docs/user_guide/diffusion/cpu_offload.md

@@ -5,7 +5,7 @@ the coarsest strategy that meets your memory target: finer-grained streaming
 saves more device memory but adds more transfer and setup overhead.
 
 For the shared factory, discovery, and lifecycle contract, see the
-[CPU Offloading design](../../design/feature/cpu_offloading.md).
+[CPU Offloading design](../../design/feature/offloader/README.md).
 
 ## Choose a strategy
 

docs/user_guide/diffusion/offloader/cpu_offload.md

@@ -77,5 +77,5 @@ while reusing sequential `.to()` movers.
 - Higher cold-start latency.
 - Transfers between encoder and denoising phases add latency.
 
-See the [model-level design](../../../design/feature/model_level_offload.md)
+See the [model-level design](../../../design/feature/offloader/cpu_offload.md)
 for lifecycle and extension invariants.

docs/user_guide/diffusion/offloader/distributed_layerwise_offload.md

@@ -5,7 +5,7 @@ deployments. With AllGather enabled, each rank stores roughly `1 / dp_size` of
 the host weights and reconstructs each layer at runtime. Without AllGather,
 each rank streams its standard-loader rank-local weights independently.
 
-See the [DLO feature design](../../../design/feature/distributed_layerwise_offload.md)
+See the [DLO feature design](../../../design/feature/offloader/distributed_layerwise_offload.md)
 for the implementation contract and compatibility matrix.
 
 ## Execution model

docs/user_guide/diffusion/offloader/layerwise_offload.md

@@ -53,7 +53,7 @@ class Flux2Transformer2DModel(nn.Module):
     ]
 ```
 
-See the [layerwise design](../../../design/feature/layerwise_offload.md) for
+See the [layerwise design](../../../design/feature/offloader/layerwise_offload.md) for
 the discovery and hook invariants. `OffloadPlan` is a separate declarative
 topology path for distributed layerwise offload.
 

mkdocs.yml

@@ -79,6 +79,10 @@ plugins:
         user_guide/quantization/index.md: user_guide/quantization/overview.md
         design/feature/diffusion_request_level_batching.md: design/feature/diffusion_continuous_batching.md
         design/feature/diffusion_step_execution.md: design/feature/diffusion_continuous_batching.md
+        design/feature/cpu_offloading.md: design/feature/offloader/README.md
+        design/feature/model_level_offload.md: design/feature/offloader/cpu_offload.md
+        design/feature/layerwise_offload.md: design/feature/offloader/layerwise_offload.md
+        design/feature/distributed_layerwise_offload.md: design/feature/offloader/distributed_layerwise_offload.md
   - glightbox
   - git-revision-date-localized:
       # exclude files