[diffusion] chore: retire released warmup and decoder flags (#33850)

docs/cookbook/diffusion/SANA-WM/SANA-WM.mdx

@@ -207,7 +207,7 @@ Notes on launch behavior:
 - **CPU offload flags are optional.** `--dit-cpu-offload`, `--text-encoder-cpu-offload`, and `--image-encoder-cpu-offload` are available; defaults are auto-adjusted from GPU memory (GPUs under 30 GB get more aggressive offloading).
 - **Multi-GPU realtime.** Prefer explicit sequence parallelism (`--sp-degree` equal to the number of GPUs for a single session). Do not enable CFG parallel for the realtime profile: the default realtime request uses `guidance_scale=1.0`, while CFG parallel requires active cond/uncond branches.
 - **FSDP.** Use `--use-fsdp-inference` only when you specifically need weight sharding for memory. For the low-latency realtime profile, prefer keeping components resident and using SP first.
-- **Warmup.** Server warmup is **automatically skipped** for the realtime pipeline — a synthetic warmup request has no WebSocket session, so the server detects the registered realtime adapter and skips it. No `--warmup` flag is needed.
+- **Warmup.** Server warmup is **automatically skipped** for the realtime pipeline — a synthetic warmup request has no WebSocket session, so the server detects the registered realtime adapter and skips it. No explicit `--warmup-mode` setting is needed.
 
 Once up, the realtime WebSocket endpoint lives at `ws://127.0.0.1:30000/v1/realtime_video/generate` (use the Python client in §7 to connect — plain `curl` does not speak the `ws://` upgrade).
 

docs/docs/sglang-diffusion/cache_dit.mdx

@@ -254,7 +254,7 @@ Then, apply the quantization config from yaml. Please also enable torch.compile
 sglang generate \
   --backend diffusers \
   --model-path Qwen/Qwen-Image \
-  --warmup \
+  --warmup-mode request \
   --cache-dit-config quantize.yaml \
   --enable-torch-compile \
   --dit-cpu-offload false \

docs/docs/sglang-diffusion/disaggregation.mdx

@@ -273,10 +273,6 @@ Set `--disagg-p2p-hostname` to the actual IP on each machine. For multi-machine,
       <td><code>--decoder-sp</code></td>
       <td>Decoder sequence parallelism</td>
     </tr>
-    <tr>
-      <td><code>--decoder-tp</code></td>
-      <td>Deprecated alias for <code>--decoder-sp</code></td>
-    </tr>
   </tbody>
 </table>
 

docs/docs/sglang-diffusion/models_with_ar.mdx

@@ -122,7 +122,7 @@ SGLANG_CACHE_DIT_FN=2 SGLANG_CACHE_DIT_BN=1 SGLANG_CACHE_DIT_WARMUP=4 SGLANG_CAC
 SGLANG_CACHE_DIT_MC=4 SGLANG_CACHE_DIT_TAYLORSEER=true SGLANG_CACHE_DIT_TS_ORDER=2 \
 SGLANG_CACHE_DIT_ENABLED=true sglang generate --model-path /path/to/zai-org/GLM-Image/ \
 --prompt "A curious raccoon" --height 1920 --width 1088 --num-inference-steps 50 --num-gpus 4 \
---sp-degree 4 --srt-encoder-url "http://${HOST}:${PORT}" --warmup
+--sp-degree 4 --srt-encoder-url "http://${HOST}:${PORT}" --warmup-mode request
 ```
 Result:
 ```bash