phase 0+1: project scaffold + xserv-cuda crate

- Cargo workspace with xserv-cuda crate
- CUDA FFI bindings (cudart: memory, stream, device, error)
- GpuBuffer RAII wrapper with H2D/D2H/D2D copy
- CudaStream wrapper with RAII Drop
- CachingAllocator with size-bucketed free lists
- PinnedBuffer for page-locked host memory
- Device info query via cudaDeviceGetAttribute
- Vector-add CUDA kernel smoke test
- Integration test suite (11 tests)
- build.rs: cc crate compiles .cu for SM 12.0
- sync-and-build.sh for remote build on dash5
- Roadmap doc (docs/00-roadmap.md) and Phase 0+1 design doc

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

tools/sync-and-build.sh

@@ -0,0 +1,25 @@
+#!/bin/bash
+# Sync local project to dash5 and build/test there.
+# Usage: ./tools/sync-and-build.sh [test|build|run]
+
+set -e
+
+REMOTE="dash5"
+REMOTE_DIR="/opt/wjh/projects/xserv"
+LOCAL_DIR="$(cd "$(dirname "$0")/.." && pwd)"
+
+ACTION="${1:-build}"
+
+echo "=== Syncing to $REMOTE:$REMOTE_DIR ==="
+ssh "$REMOTE" "mkdir -p $REMOTE_DIR"
+rsync -az --delete \
+    --exclude target \
+    --exclude .git \
+    "$LOCAL_DIR/" "$REMOTE:$REMOTE_DIR/"
+
+echo "=== Running: cargo $ACTION ==="
+ssh "$REMOTE" "source \$HOME/.cargo/env && \
+    export PATH=/usr/local/cuda/bin:\$PATH && \
+    export CUDA_HOME=/usr/local/cuda && \
+    cd $REMOTE_DIR && \
+    cargo $ACTION --release 2>&1"