[Model][MiniMax-H3] Multi-GPU serving fixes and layer-wise offload component selection (#7047)

Signed-off-by: heyuanliu-intel <heyuan.liu@intel.com>

docs/design/feature/sequence_parallel.md

@@ -77,7 +77,9 @@ Use it when plain Ulysses-SP would otherwise fail because:
 
 - `auto_pad=True` pads sequence tokens in `_sp_plan` and requires attention backends that support `attention_mask`.
 - `advanced_uaa` does not depend on mask-based token padding inside Ulysses attention. It is therefore a better fit for non-divisible head counts and uneven Ulysses shard sizes.
-- `auto_pad=True` remains incompatible with Ring attention because the ring backend does not consume `attention_mask`.
+- `auto_pad=True` remains incompatible with Ring attention because the ring backend does not consume arbitrary
+  `attention_mask` values. A model with contiguous suffix padding may instead publish `valid_kv_length`; Ring trims
+  each circulated K/V block against that global valid prefix.
 - `advanced_uaa` is still experimental and hybrid mode remains limited by Ring's equal-shape requirement.
 
 ---
@@ -416,7 +418,7 @@ _sp_plan = {
 | Constraint | Description |
 |------------|-------------|
 | **Attention Backend Compatibility** | The attention backends must support `attention_mask`. Currently only `TORCH_SDPA` and `FLASH_ATTN` (default for diffusion models) are supported. |
-| **Ring Attention Limitation** | Ring attention does not support `attention_mask`. Therefore, when using `auto_pad=True`, the combination of Ulysses + Ring attention is not feasible. |
+| **Ring Attention Limitation** | Ring attention does not support arbitrary `attention_mask` values, so `auto_pad=True` remains incompatible. Contiguous suffix padding is supported when the model publishes the global `valid_kv_length` prefix. |
 
 1. Enable `auto_pad=True` for all sequence-dimension inputs in `_sp_plan`:
 ```python

docs/user_guide/diffusion/regional_compilation.md

@@ -34,5 +34,34 @@ that provide their own `setup_compile()` implementation manage their compilation
 policy independently. Compilation is lazy, so backend or graph errors can first
 surface on the initial request.
 
+## Pinning one packed shape (MiniMax-H3)
+
+Compiled regions are keyed by input shape. MiniMax-H3 packs a request into a
+row count that follows the request -- a longer prompt, more frames, a larger
+frame -- and rounds it up to the next 64-row boundary, so two requests can land
+on two different packed lengths.
+
+Under the default `diffusion_compile_dynamic: true` a new packed length is
+absorbed by the dynamic shape, so it is not by itself a recompilation. It still
+hands the backend a shape it has not autotuned, which is the risk this knob
+exists to remove: a fixed-shape deployment (`--no-diffusion-compile-dynamic`)
+recompiles the transformer blocks per shape, and a first-seen large shape can
+push autotuning into its worst-case memory use.
+
+A request pins the length with `extra_args["pad_seq_len"]`:
+
+```python
+sampling_params = SamplingParams(extra_args={"pad_seq_len": 54080})
+```
+
+The value must be a positive multiple of 64 and must cover the rows the request
+actually uses; the packed sequence is then padded to it instead of to the next
+64-row boundary. Pick a bucket that covers every request dimension the
+deployment accepts -- prompt length, frame count, frame size and reference
+blocks all change the used row count. The server logs the effective length as
+`MiniMax H3 packed sequence: ... pad_seq_len=... used=... seq_len=...` whenever
+a request pins it. The padding rows are masked out, so their cost is the
+attention and feed-forward work on those rows.
+
 Use `--enforce-eager` to disable the model runner's generic compile setup.
 Pipelines that compile internally define their own eager-mode behavior.