phase 4: transformer core kernels

CUDA kernels (csrc/):
- common.cuh: shared warp_reduce_sum/max, block_reduce_sum/max
- normalization/rmsnorm.cu: RMSNorm (F32 + BF16)
- normalization/layernorm.cu: LayerNorm with Welford (F32 + BF16)
- activation/activations.cu: GELU tanh-approx + SiLU (F32 + BF16)
- reduce/softmax.cu: safe softmax, 3-pass (F32 + BF16)
- embedding/embedding.cu: gather lookup (F32 + BF16)
- embedding/rope.cu: RoPE in-place + precomputed cos/sin cache (F32 + BF16)

Rust wrappers (xserv-kernels/src/):
- rmsnorm.rs, layernorm.rs, activation.rs, softmax.rs, embedding.rs, rope.rs
- RopeCache struct with GPU-side precomputation

Tests: 12 new tests (ops_test.rs), all passing with good precision:
- F32: max_err 1e-6 ~ 1e-9
- BF16: max_err 2e-3 ~ 7e-3
Total: 29 kernel tests + 27 prior = 56 tests passing

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

crates/xserv-kernels/src/rmsnorm.rs

@@ -0,0 +1,37 @@
+use std::ffi::c_void;
+use xserv_tensor::{DType, Device, Tensor};
+
+unsafe extern "C" {
+    fn launch_rmsnorm_f32(x: *const c_void, gamma: *const c_void, out: *mut c_void,
+                          rows: i32, hidden_size: i32, eps: f32, stream: *mut c_void);
+    fn launch_rmsnorm_bf16(x: *const c_void, gamma: *const c_void, out: *mut c_void,
+                           rows: i32, hidden_size: i32, eps: f32, stream: *mut c_void);
+}
+
+pub fn rmsnorm(x: &Tensor, gamma: &Tensor, eps: f32) -> Tensor {
+    assert!(x.ndim() >= 1);
+    assert!(x.is_contiguous() && gamma.is_contiguous());
+    assert!(matches!(x.device(), Device::Cuda(_)));
+    let hidden_size = *x.shape().last().unwrap();
+    assert_eq!(gamma.shape(), &[hidden_size]);
+    assert_eq!(x.dtype(), gamma.dtype());
+
+    let rows = x.numel() / hidden_size;
+    let out = Tensor::zeros(x.shape(), x.dtype(), x.device());
+
+    unsafe {
+        match x.dtype() {
+            DType::F32 => launch_rmsnorm_f32(
+                x.data_ptr() as _, gamma.data_ptr() as _, out.data_ptr() as *mut c_void,
+                rows as i32, hidden_size as i32, eps, std::ptr::null_mut(),
+            ),
+            DType::BF16 => launch_rmsnorm_bf16(
+                x.data_ptr() as _, gamma.data_ptr() as _, out.data_ptr() as *mut c_void,
+                rows as i32, hidden_size as i32, eps, std::ptr::null_mut(),
+            ),
+            _ => panic!("unsupported dtype for rmsnorm"),
+        }
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}