feat(attention): add single-gpu comparison harness

pyproject.toml

@@ -0,0 +1,52 @@
+[build-system]
+requires = ["setuptools>=64", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "RL-Kernel"
+version = "0.1.0"
+description = "High-performance RL training engine focused on kernel fusion and memory efficiency."
+readme = "README.md"
+requires-python = ">=3.10"
+license = {text = "Apache-2.0"}
+authors = [
+    {name = "RL-Kernel Contributors"}
+]
+dependencies = [
+    "torch>=2.4.1",
+    "tabulate",
+    "numpy",
+    "accelerate",
+    "transformers==5.13.1",
+]
+
+[project.optional-dependencies]
+cuda = ["flashinfer-python>=0.1.6", "nvidia-ml-py"]
+rocm = ["aiter"]
+vllm = ["vllm>=0.6.0"]
+drift-viewer = ["Pillow>=10", "PySide6>=6.6"]
+dev = ["pytest", "black", "isort", "ruff", "mypy", "pre-commit"]
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["rl_engine*"]
+
+[tool.ruff]
+line-length = 100
+
+[tool.ruff.lint]
+select = ["E", "F", "B"]
+ignore = []
+
+[tool.ruff.lint.per-file-ignores]
+"__init__.py" = ["F401"]
+
+[tool.mypy]
+ignore_missing_imports = true
+follow_imports = "silent"
+
+[tool.pytest.ini_options]
+markers = [
+    "smoke_operator: temporary smoke-only operator plumbing tests",
+    "unit: CPU-safe unit tests",
+]

rl_engine/testing/__init__.py

@@ -25,6 +25,9 @@
     run_full_attention,
     run_fused_like_rope_attention,
     run_paged_kv_attention,
+    run_strict_shared_core_attention,
+    run_strict_shared_core_chunked_attention,
+    run_strict_shared_core_paged_layout_attention,
     run_unfused_rope_attention,
     transformer_engine_context_parallel_available,
 )
@@ -96,6 +99,9 @@
     "run_full_attention",
     "run_paged_kv_attention",
     "run_unfused_rope_attention",
+    "run_strict_shared_core_attention",
+    "run_strict_shared_core_chunked_attention",
+    "run_strict_shared_core_paged_layout_attention",
     "reference_payload",
     "restore_logical_order",
     "restore_logical_order_from_padded",