[Doc][Misc]Add sleep mode documentation for unquantized MoE models (vllm-project#11110)

### What this PR does / why we need it?
Adds a "MoE vs. dense (non-MoE) model differences" section to the sleep
mode guide, documenting the expert weight layout restoration:
process_weights_after_loading() transposes w13_weight/w2_weight into the
torch_npu.npu_grouped_matmul layout at load time (assuming standard
checkpoint layout, no validation), and wake_up() re-applies the same
transpose after the allocator restores memory; dense/quantized models
skip it.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?


- vLLM version: v0.23.0
- vLLM main:
vllm-project/vllm@967c5c3

---------

Co-authored-by: yjyang62 <yjyang62@users.noreply.github.com>

Author: yjyang62

docs/source/user_guide/feature_guide/sleep_mode.md

@@ -67,6 +67,19 @@ llm.wake_up(tags=["kv_cache"])
 
 With extra cleanup enabled, ACL graphs are recaptured only when `tags` is `None` or contains `"kv_cache"`. This avoids recapturing graphs before externally reloaded weights and KV-cache state are ready.
 
+### Expert weight layout restoration
+
+For dense models, `wake_up()` simply restores the model weights to NPU memory; the tensor layout is unchanged.
+
+For **unquantized MoE models** (`quant_config is None`), the fused expert weights are stored in a transposed layout for NPU matmul efficiency. This layout is produced once at model load time by `process_weights_after_loading()`: after the weights are loaded, the method transposes the second and third dimensions (`transpose(1, 2)`) of `w13_weight` and `w2_weight` to convert the standard checkpoint layout into the format required by the `torch_npu.npu_grouped_matmul` operator.
+
+After the sleep-mode allocator restores the original (untransposed) memory, `wake_up()` re-applies the same transpose to the affected expert weights when the `"weights"` tag is being restored:
+
+- `w13_weight` (gate/up projection): transposed back to the runtime layout when its second dimension matches `hidden_size`;
+- `w2_weight` (down projection): transposed back to the runtime layout when its third dimension matches `hidden_size`.
+
+This step is skipped entirely for dense models (which have no expert weights) and for quantized models (whose weights are handled by the quantization method).
+
 ## Usage
 
 The following is a simple example of how to use sleep mode.