phase 15: Tensor::empty + CUDA Graph infra — 50.3 tok/s (140% of HF, 45% roofline)

Two optimizations:

1. Tensor::empty() — skip cudaMemset for output tensors
   All kernel wrappers that fully overwrite their output now use
   Tensor::empty() instead of Tensor::zeros(). Eliminates ~756
   cudaMemset calls per decode step (21 per layer × 36 layers).
   Improvement: 46.6 → 50.3 tok/s (+8%).

2. CUDA Graph infrastructure (for future use)
   Added FFI bindings (cudaStreamBeginCapture, cudaGraphInstantiate,
   cudaGraphLaunch) and RAII CudaGraph wrapper. Not yet used in the
   forward pass due to variable kv_len, but provides foundation for
   future graph-based decode optimization.

Ablation (dash5, RTX 5090, Qwen3-8B BF16, serial decode):

| Optimization | tok/s | vs HF | Roofline |
|-------------|-------|-------|----------|
| Phase 14 baseline | 12.9 | 36% | 12% |
| + Fused kernels | 13.2 | 37% | 12% |
| + Batched decode | 13.2 (serial) | 37% | 12% |
| + Custom GEMV | 46.6 | 130% | 42% |
| + Tensor::empty | 50.3 | 140% | 45% |

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

crates/xserv-kernels/src/embedding.rs

@@ -29,7 +29,7 @@ pub fn embedding(table: &Tensor, token_ids: &[u32]) -> Tensor {
     let mut ids_gpu = GpuBuffer::alloc(ids_bytes.len()).expect("alloc token_ids");
     ids_gpu.copy_from_host(ids_bytes).unwrap();
 
-    let out = Tensor::zeros(&[num_tokens, hidden_size], table.dtype(), table.device());
+    let out = Tensor::empty(&[num_tokens, hidden_size], table.dtype(), table.device());
 
     unsafe {
         match table.dtype() {