docs(cookbook): Qwen3.5 FP8 on B200/B300 — trtllm-gen MoE + symm mem (#38374)

Co-authored-by: Po-Han Huang <pohanh@nvidia.com>

docs/src/snippets/autoregressive/qwen35-deployment.jsx

@@ -410,8 +410,9 @@ export const Qwen35Deployment = () => {
       }
     }
 
-    // Enable NCCL symmetric memory for H100 FP8 deployments.
-    if (hardware === 'h100' && quantization === 'fp8' && hwConfig.tp > 1) {
+    // Enable NCCL symmetric memory for H100 and Blackwell FP8 deployments.
+    const symmMemFp8Hw = ['h100', 'b200', 'b300'];
+    if (symmMemFp8Hw.includes(hardware) && quantization === 'fp8' && hwConfig.tp > 1) {
       cmd += ` \\\n  --enable-symm-mem`;
     }
 
@@ -455,6 +456,16 @@ export const Qwen35Deployment = () => {
       cmd += ` \\\n  --attention-backend flashinfer`;
     }
 
+    // Enable FlashInfer GDN (linear attention) prefill for Blackwell FP8 deployments.
+    if ((hardware === 'b200' || hardware === 'b300') && quantization === 'fp8') {
+      cmd += ` \\\n  --linear-attn-prefill-backend flashinfer`;
+    }
+
+    // Enable FlashInfer trtllm MoE for FP8 Blackwell deployments for MoE models.
+    if ((hardware === 'b200' || hardware === 'b300') && quantization === 'fp8' && MOE_MODELS.has(model)) {
+      cmd += ` \\\n  --moe-runner-backend flashinfer_trtllm`;
+    }
+
     // Append AMD GPU-specific backend configurations.
     // All AMD MI GPUs use the AITER unified-attention backend (pair with
     // SGLANG_USE_AITER=1 and SGLANG_USE_AITER_UNIFIED_ATTN=1; see cookbook prose),