perf: GPU transpose/reshape/repeat_kv kernels (eliminate CPU round-trips)

New CUDA kernels (csrc/embedding/transpose.cu):
- reshape_heads_bf16: [S, H*D] → [1, H, S, D]
- merge_heads_bf16: [1, H, S, D] → [S, H*D]
- transpose_hsd_to_shd_bf16: [1, H, S, D] → [S, H, D] (for RoPE)
- transpose_shd_to_hsd_bf16: [S, H, D] → [1, H, S, D] (from RoPE)
- repeat_kv_bf16: [1, KV_H, S, D] → [1, KV_H*n_rep, S, D]

Rust wrappers (xserv-kernels/src/transpose.rs):
- reshape_heads_gpu, merge_heads_gpu, transpose_for/from_rope_gpu, repeat_kv_gpu

Qwen3 forward_gpu_cache now uses all GPU kernels — zero CPU data round-trips.

Result: 50/50 self-consistent, 3-5% faster (TBT 142→137ms)
Remaining bottleneck: ~900 device::synchronize() calls + 252 cuBLAS handle
creations per token (Phase 15 targets)

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

crates/xserv-kernels/src/transpose.rs

@@ -0,0 +1,91 @@
+use std::ffi::c_void;
+use xserv_tensor::{DType, Device, Tensor};
+
+unsafe extern "C" {
+    fn launch_reshape_heads_bf16(inp: *const c_void, out: *mut c_void, seq_len: i32, num_heads: i32, head_dim: i32, stream: *mut c_void);
+    fn launch_merge_heads_bf16(inp: *const c_void, out: *mut c_void, seq_len: i32, num_heads: i32, head_dim: i32, stream: *mut c_void);
+    fn launch_transpose_hsd_to_shd_bf16(inp: *const c_void, out: *mut c_void, seq_len: i32, num_heads: i32, head_dim: i32, stream: *mut c_void);
+    fn launch_transpose_shd_to_hsd_bf16(inp: *const c_void, out: *mut c_void, seq_len: i32, num_heads: i32, head_dim: i32, stream: *mut c_void);
+    fn launch_repeat_kv_bf16(inp: *const c_void, out: *mut c_void, kv_heads: i32, n_rep: i32, seq_len: i32, head_dim: i32, stream: *mut c_void);
+}
+
+/// [S, H*D] → [1, H, S, D] on GPU (BF16)
+pub fn reshape_heads_gpu(x: &Tensor, seq_len: usize, num_heads: usize, head_dim: usize) -> Tensor {
+    assert_eq!(x.dtype(), DType::BF16);
+    assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
+    let out = Tensor::zeros(&[1, num_heads, seq_len, head_dim], DType::BF16, x.device());
+    unsafe {
+        launch_reshape_heads_bf16(
+            x.data_ptr() as _, out.data_ptr() as *mut c_void,
+            seq_len as i32, num_heads as i32, head_dim as i32, std::ptr::null_mut(),
+        );
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}
+
+/// [1, H, S, D] → [S, H*D] on GPU (BF16)
+pub fn merge_heads_gpu(x: &Tensor, seq_len: usize, num_heads: usize, head_dim: usize) -> Tensor {
+    assert_eq!(x.dtype(), DType::BF16);
+    assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
+    let hidden = num_heads * head_dim;
+    let out = Tensor::zeros(&[seq_len, hidden], DType::BF16, x.device());
+    unsafe {
+        launch_merge_heads_bf16(
+            x.data_ptr() as _, out.data_ptr() as *mut c_void,
+            seq_len as i32, num_heads as i32, head_dim as i32, std::ptr::null_mut(),
+        );
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}
+
+/// [1, H, S, D] → [S, H, D] for RoPE on GPU (BF16)
+pub fn transpose_for_rope_gpu(x: &Tensor, seq_len: usize, num_heads: usize, head_dim: usize) -> Tensor {
+    assert_eq!(x.dtype(), DType::BF16);
+    assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
+    let out = Tensor::zeros(&[seq_len, num_heads, head_dim], DType::BF16, x.device());
+    unsafe {
+        launch_transpose_hsd_to_shd_bf16(
+            x.data_ptr() as _, out.data_ptr() as *mut c_void,
+            seq_len as i32, num_heads as i32, head_dim as i32, std::ptr::null_mut(),
+        );
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}
+
+/// [S, H, D] → [1, H, S, D] after RoPE on GPU (BF16)
+pub fn transpose_from_rope_gpu(x: &Tensor, seq_len: usize, num_heads: usize, head_dim: usize) -> Tensor {
+    assert_eq!(x.dtype(), DType::BF16);
+    assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
+    let out = Tensor::zeros(&[1, num_heads, seq_len, head_dim], DType::BF16, x.device());
+    unsafe {
+        launch_transpose_shd_to_hsd_bf16(
+            x.data_ptr() as _, out.data_ptr() as *mut c_void,
+            seq_len as i32, num_heads as i32, head_dim as i32, std::ptr::null_mut(),
+        );
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}
+
+/// [1, KV_H, S, D] → [1, KV_H*n_rep, S, D] on GPU (BF16)
+pub fn repeat_kv_gpu(x: &Tensor, n_rep: usize) -> Tensor {
+    if n_rep == 1 { return x.clone(); }
+    assert_eq!(x.dtype(), DType::BF16);
+    assert!(x.is_contiguous() && matches!(x.device(), Device::Cuda(_)));
+    let kv_heads = x.shape()[1];
+    let seq_len = x.shape()[2];
+    let head_dim = x.shape()[3];
+    let new_heads = kv_heads * n_rep;
+    let out = Tensor::zeros(&[1, new_heads, seq_len, head_dim], DType::BF16, x.device());
+    unsafe {
+        launch_repeat_kv_bf16(
+            x.data_ptr() as _, out.data_ptr() as *mut c_void,
+            kv_heads as i32, n_rep as i32, seq_len as i32, head_dim as i32, std::ptr::null_mut(),
+        );
+    }
+    xserv_cuda::device::synchronize().unwrap();
+    out
+}