kernels/cuda: paged-attention kernel, dispatch, pinned host memory

CUDA layer for the paged-KV + swap work:
- csrc: new paged_attention.cu plus updates across attention/gemm/norm/
  activation/embedding/reduce kernels and common.cuh.
- xserv-kernels: new dispatch module and kernel-binding updates.
- xserv-cuda: cudaMallocHost/FreeHost bindings + PinnedBuffer (host swap
  pool backing) and offset-aware D2H/H2D copies used to move KV blocks
  between the GPU pool and pinned host memory.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

crates/xserv-kernels/src/embedding.rs

@@ -4,9 +4,9 @@ use xserv_tensor::{DType, Device, Tensor};
 
 unsafe extern "C" {
     fn launch_embedding_f32(table: *const c_void, token_ids: *const c_void, out: *mut c_void,
-                            num_tokens: i32, hidden_size: i32, stream: *mut c_void);
+                            num_tokens: i32, hidden_size: i32, vocab_size: i32, stream: *mut c_void);
     fn launch_embedding_bf16(table: *const c_void, token_ids: *const c_void, out: *mut c_void,
-                             num_tokens: i32, hidden_size: i32, stream: *mut c_void);
+                             num_tokens: i32, hidden_size: i32, vocab_size: i32, stream: *mut c_void);
 }
 
 /// Embedding lookup: table[token_ids[i]] for each i.
@@ -18,6 +18,9 @@ pub fn embedding(table: &Tensor, token_ids: &[u32]) -> Tensor {
 
     let hidden_size = table.shape()[1];
     let num_tokens = token_ids.len();
+    let vocab_size = table.shape()[0];
+    assert!(num_tokens <= i32::MAX as usize, "too many tokens for i32 kernel param");
+    assert!(hidden_size <= i32::MAX as usize, "hidden_size too large for i32 kernel param");
 
     // Upload token_ids to GPU
     let ids_bytes = unsafe {
@@ -29,6 +32,10 @@ pub fn embedding(table: &Tensor, token_ids: &[u32]) -> Tensor {
     let mut ids_gpu = xserv_cuda::allocator::cached_alloc(ids_bytes.len()).expect("alloc token_ids");
     ids_gpu.copy_from_host(ids_bytes).unwrap();
 
+    for &tid in token_ids {
+        assert!((tid as usize) < vocab_size, "token_id {tid} out of bounds (vocab_size={vocab_size})");
+    }
+
     let out = Tensor::empty(&[num_tokens, hidden_size], table.dtype(), table.device());
 
     unsafe {
@@ -36,12 +43,12 @@ pub fn embedding(table: &Tensor, token_ids: &[u32]) -> Tensor {
             DType::F32 => launch_embedding_f32(
                 table.data_ptr() as _, ids_gpu.as_ptr() as _,
                 out.data_ptr() as *mut c_void,
-                num_tokens as i32, hidden_size as i32, std::ptr::null_mut(),
+                num_tokens as i32, hidden_size as i32, vocab_size as i32, std::ptr::null_mut(),
             ),
             DType::BF16 => launch_embedding_bf16(
                 table.data_ptr() as _, ids_gpu.as_ptr() as _,
                 out.data_ptr() as *mut c_void,
-                num_tokens as i32, hidden_size as i32, std::ptr::null_mut(),
+                num_tokens as i32, hidden_size as i32, vocab_size as i32, std::ptr::null_mut(),
             ),
             _ => panic!("unsupported dtype for embedding"),
         }