重构body api，性能分析，项目整理

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "CelerisLab"
-version = "0.2.0"
+version = "0.3.0"
 description = "GPU-accelerated Lattice Boltzmann Method (LBM) CFD solver using CUDA"
 readme = "README.md"
 requires-python = ">=3.8"
@@ -42,4 +42,4 @@ package-dir = {"" = "src"}
 where = ["src"]
 
 [tool.setuptools.package-data]
-"CelerisLab.lbm" = ["kernels/*.cu", "kernels/*.h", "configs/*.json"]
+"CelerisLab" = ["lbm/kernels/**/*.cu", "lbm/kernels/**/*.cuh", "lbm/kernels/**/*.h", "configs/*.json"]