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>

csrc/embedding/embedding.cu

@@ -1,4 +1,5 @@
 #include <cuda_bf16.h>
+#include "../common.cuh"
 
 // Embedding lookup: out[seq_idx] = table[token_ids[seq_idx]]
 // Grid: num_tokens, Block: handles hidden_size elements per token.
@@ -7,10 +8,12 @@ __global__ void embedding_f32(
     const float* __restrict__ table,    // [vocab_size, hidden_size]
     const int* __restrict__ token_ids,  // [num_tokens]
     float* __restrict__ out,            // [num_tokens, hidden_size]
-    int hidden_size
+    int hidden_size,
+    int vocab_size
 ) {
     int token_idx = blockIdx.x;
     int tid = token_ids[token_idx];
+    if (tid < 0 || tid >= vocab_size) return;
     const float* row = table + tid * hidden_size;
     float* dst = out + token_idx * hidden_size;
 
@@ -23,10 +26,12 @@ __global__ void embedding_bf16(
     const __nv_bfloat16* __restrict__ table,
     const int* __restrict__ token_ids,
     __nv_bfloat16* __restrict__ out,
-    int hidden_size
+    int hidden_size,
+    int vocab_size
 ) {
     int token_idx = blockIdx.x;
     int tid = token_ids[token_idx];
+    if (tid < 0 || tid >= vocab_size) return;
     const __nv_bfloat16* row = table + tid * hidden_size;
     __nv_bfloat16* dst = out + token_idx * hidden_size;
 
@@ -38,18 +43,20 @@ __global__ void embedding_bf16(
 extern "C" {
 
 void launch_embedding_f32(const void* table, const void* token_ids, void* out,
-                          int num_tokens, int hidden_size, void* stream) {
+                          int num_tokens, int hidden_size, int vocab_size, void* stream) {
     int block = (hidden_size < 256) ? hidden_size : 256;
     embedding_f32<<<num_tokens, block, 0, (cudaStream_t)stream>>>(
-        (const float*)table, (const int*)token_ids, (float*)out, hidden_size);
+        (const float*)table, (const int*)token_ids, (float*)out, hidden_size, vocab_size);
+    CUDA_CHECK_LAST_ERROR();
 }
 
 void launch_embedding_bf16(const void* table, const void* token_ids, void* out,
-                           int num_tokens, int hidden_size, void* stream) {
+                           int num_tokens, int hidden_size, int vocab_size, void* stream) {
     int block = (hidden_size < 256) ? hidden_size : 256;
     embedding_bf16<<<num_tokens, block, 0, (cudaStream_t)stream>>>(
         (const __nv_bfloat16*)table, (const int*)token_ids,
-        (__nv_bfloat16*)out, hidden_size);
+        (__nv_bfloat16*)out, hidden_size, vocab_size);
+    CUDA_CHECK_LAST_ERROR();
 }
 
 }