style: format Rust workspace

crates/xserv-cuda/tests/integration.rs

@@ -14,7 +14,10 @@ fn test_device_info() {
         info.compute_major, info.compute_minor
     );
     println!("  SM Count: {}", info.sm_count);
-    println!("  Shared Mem/Block: {} KB", info.shared_mem_per_block / 1024);
+    println!(
+        "  Shared Mem/Block: {} KB",
+        info.shared_mem_per_block / 1024
+    );
     println!("  Warp Size: {}", info.warp_size);
     println!("  Max Threads/Block: {}", info.max_threads_per_block);
 
@@ -145,7 +148,11 @@ fn test_caching_allocator() {
 
     // Second allocation of same size: should hit cache
     let _buf2 = alloc.alloc(1024).unwrap();
-    assert_eq!(alloc.stats().cuda_malloc_count, 1, "should reuse cached buffer");
+    assert_eq!(
+        alloc.stats().cuda_malloc_count,
+        1,
+        "should reuse cached buffer"
+    );
     assert_eq!(alloc.stats().cache_hit_count, 1);
 }
 
@@ -198,11 +205,17 @@ fn test_async_copy() {
     }
 
     let mut gpu = GpuBuffer::alloc(4096).unwrap();
-    unsafe { gpu.copy_from_host_async(pinned.as_slice(), &stream).unwrap() };
+    unsafe {
+        gpu.copy_from_host_async(pinned.as_slice(), &stream)
+            .unwrap()
+    };
     stream.synchronize().unwrap();
 
     let mut out_pinned = PinnedBuffer::alloc(4096).unwrap();
-    unsafe { gpu.copy_to_host_async(out_pinned.as_mut_slice(), &stream).unwrap() };
+    unsafe {
+        gpu.copy_to_host_async(out_pinned.as_mut_slice(), &stream)
+            .unwrap()
+    };
     stream.synchronize().unwrap();
 
     assert_eq!(pinned.as_slice(), out_pinned.as_slice());