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

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