[NPU][Diffusion] Optimize SenseNova-U1 batched generation (#39382)

Signed-off-by: syd520zy <529477025@qq.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>

docs/cookbook/diffusion/SenseNova/SenseNova-U1.5-8B-MoT.mdx

@@ -78,11 +78,38 @@ with open("output_sensenova_u15.png", "wb") as f:
     f.write(image_bytes)
 ```
 
-## 5. Benchmark
+## 5. Advanced usage
 
-### 5.1 Speedup Benchmark
+### 5.1 Dynamic request batching
 
-#### 5.1.1 Single-run Profile
+Start the server with dynamic batching enabled:
+
+```bash Command
+sglang serve \
+  --model-path sensenova/SenseNova-U1.5-8B-MoT \
+  --port 30000 \
+  --batching-max-size 2 \
+  --batching-delay-ms 100
+```
+
+Submit requests concurrently so they arrive within the batching delay. Requests
+in one batch must use the same resolution, inference steps, guidance settings,
+and output options. Requests with multiple outputs or `think_mode=true` are
+executed sequentially.
+
+### 5.2 Ascend NPU optimizations
+
+On Ascend NPU, SenseNova-U1 automatically uses fused inference attention,
+RMSNorm, and SwiGLU MLP operators for supported inputs. FIA and SwiGLU fall back
+when their requirements are not met. Run one complete warmup request before
+benchmarking because the fused MLP packs its gate and up projection weights on
+first use.
+
+## 6. Benchmark
+
+### 6.1 Speedup benchmark
+
+#### 6.1.1 Single-run profile
 
 <Tabs>
   <Tab title="NVIDIA A800">
@@ -137,4 +164,21 @@ with open("output_sensenova_u15.png", "wb") as f:
     ------------------------------------------------------------
     ```
   </Tab>
+  <Tab title="Ascend 910C">
+
+    Environment: one Ascend 910C; workload: four concurrent 2048 x 2048
+    text-to-image requests, 50 denoising steps, CFG 4, BF16.
+
+    | Batch size | NPU operators | Duration (s) | Throughput (images/s) | Mean latency (s) | Peak reserved memory (MB) |
+    |---:|---|---:|---:|---:|---:|
+    | 1 | Disabled | 234.28 | 0.01707 | 146.47 | 35698 |
+    | 2 | Disabled | 234.83 | 0.01703 | 176.06 | 37870 |
+    | 1 | FIA + RMSNorm + SwiGLU | 205.94 | 0.01942 | 128.80 | 35718 |
+    | 2 | FIA + RMSNorm + SwiGLU | 195.02 | 0.02051 | 146.33 | 37850 |
+
+    Optimized B1 improves throughput by 13.76% over unoptimized B1. Optimized
+    B2 improves throughput by 20.42% over unoptimized B2 and by 5.60% over
+    optimized B1.
+
+  </Tab>
 </Tabs>