phase 15: decode attention kernel + fused silu_mul + fused add_rmsnorm

Three performance optimizations targeting decode throughput:

1. Decode Attention Kernel (csrc/attention/flash_attention.cu):
   - Specialized kernel for Q_len=1 (decode step)
   - 256 threads parallelize across KV sequence dimension
   - Online softmax with block-level warp-shuffle reduction
   - Replaces FA2 kernel which wasted 63/64 threads for decode
   - flash_attention() auto-dispatches when q_len==1

2. Fused SiLU×Mul (csrc/activation/activations.cu):
   - Single kernel: out = silu(gate) * up
   - Saves 1 HBM read + 1 HBM write per FFN layer (N elements)
   - Eliminates intermediate tensor allocation

3. Fused Add+RMSNorm (csrc/normalization/rmsnorm.cu):
   - Single kernel: (normed, sum) = (rmsnorm(x+residual), x+residual)
   - Saves 1 full HBM round-trip per attention block
   - Eliminates separate add + rmsnorm kernel pair

Performance analysis:
- At current short sequences (max 79 tokens), these optimizations provide
  marginal benefit because the bottleneck is cuBLAS GEMV overhead:
  252 weight matrix reads × ~32MB each = 15.5 GB per decode step.
  Theoretical minimum at 1.79 TB/s = 8.7ms, actual ~78ms (9x gap).
- The fused kernels and decode attention will show larger gains at
  longer sequences where attention and element-wise ops dominate.
- Next optimization target: CUDA Graphs to eliminate kernel launch
  overhead, or custom GEMV kernels to replace cuBLAS for M=1.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

crates/xserv-model/src/qwen3.rs

@@ -196,14 +196,15 @@ impl Qwen3 {
             // GPU merge_heads: [1, H, S, D] → [S, H*D]
             let attn_merged = xserv_kernels::merge_heads_gpu(&attn_out, new_tokens, num_heads, head_dim);
             let attn_proj = matmul_2d(&attn_merged, &layer.o_proj_wt);
-            x = add_any(&residual, &attn_proj);
 
-            let residual = x.clone();
-            let normed = rmsnorm(&x, &layer.post_norm, eps);
+            // Fused add + rmsnorm: (normed, x) where x = residual + attn_proj
+            let (normed, x_new) = xserv_kernels::add_rmsnorm(&attn_proj, &residual, &layer.post_norm, eps);
+            let residual = x_new.clone();
+
+            // Fused SiLU×Mul
             let gate = matmul_2d(&normed, &layer.gate_proj_wt);
             let up = matmul_2d(&normed, &layer.up_proj_wt);
-            let gate_activated = silu(&gate);
-            let hidden_states = mul_any(&gate_activated, &up);
+            let hidden_states = xserv_kernels::silu_mul(&gate, &up);
             let down = matmul_2d(&hidden_states, &layer.down_proj_wt);
             x = add_any(&residual, &down);
         }