docs: organize offloader feature designs

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

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.