[MUH] Fix three-layer disconnect — C++ headers are now the single source of truth

Problems fixed:
  1. gen_patch.py was reading .muh YAML (all nulls) instead of C++ headers.
     Now it parses bi100_* structs directly from tuning_*.cuh via regex,
     extracts constexpr values, and maps them to vllm injection points.
     Verified: 11 patches generated from 6 algorithms.

  2. C++ headers had no build system or tests.
     Added CMakeLists.txt (header-only library target) and compile_test.cpp.
     Verified: g++ -std=c++17 compiles all headers, 17/17 runtime checks pass.
     Also added cuda_compile_test.cu for when nvcc is available.

  3. baseline.muh had a tuning section full of nulls duplicating C++ values.
     Stripped to vllm launch config only. Tuning values live exclusively
     in muh/include/muh/tuning/tuning_*.cuh bi100_* structs.

  4. Fixed constexpr goto in tuning_scan.cuh (C++17 doesn't allow goto in
     constexpr; replaced with early-return + default: break pattern).

Data flow is now:
  tuning_*.cuh (bi100_* constexpr) ──→ gen_patch.py ──→ vllm patches
  baseline.muh (launch config)     ──→ gen_yaml.py  ──→ computility-run.yaml
  compile_test.cpp                 ──→ g++/nvcc     ──→ verify values are real

muh/include/CMakeLists.txt

@@ -0,0 +1,40 @@
+cmake_minimum_required(VERSION 3.18)
+project(muh LANGUAGES CXX)
+
+# muh is a header-only library
+add_library(muh INTERFACE)
+target_include_directories(muh INTERFACE ${CMAKE_CURRENT_SOURCE_DIR})
+target_compile_features(muh INTERFACE cxx_std_17)
+
+# If CCCL is available, link it
+if(EXISTS "${CMAKE_CURRENT_SOURCE_DIR}/../../cccl_upstream/cub/cub/config.cuh")
+  target_include_directories(muh INTERFACE
+    ${CMAKE_CURRENT_SOURCE_DIR}/../../cccl_upstream/cub
+    ${CMAKE_CURRENT_SOURCE_DIR}/../../cccl_upstream/thrust
+    ${CMAKE_CURRENT_SOURCE_DIR}/../../cccl_upstream/libcudacxx/include
+  )
+  target_compile_definitions(muh INTERFACE MUH_HAS_CCCL=1)
+endif()
+
+# Compile test — verifies all headers parse without errors
+# This is a host-only test (no GPU needed)
+option(MUH_BUILD_TESTS "Build muh compile tests" ON)
+
+if(MUH_BUILD_TESTS)
+  add_executable(muh_compile_test
+    ${CMAKE_CURRENT_SOURCE_DIR}/../test/compile_test.cpp
+  )
+  target_link_libraries(muh_compile_test PRIVATE muh)
+
+  # If we have a CUDA compiler, also test .cu compilation
+  include(CheckLanguage)
+  check_language(CUDA)
+  if(CMAKE_CUDA_COMPILER)
+    enable_language(CUDA)
+    add_executable(muh_cuda_compile_test
+      ${CMAKE_CURRENT_SOURCE_DIR}/../test/cuda_compile_test.cu
+    )
+    target_link_libraries(muh_cuda_compile_test PRIVATE muh)
+    set_target_properties(muh_cuda_compile_test PROPERTIES CUDA_STANDARD 17)
+  endif()
+endif()

muh/include/muh/tuning/tuning_scan.cuh

@@ -200,10 +200,8 @@ struct policy_selector {
 
   /// Get the best lookback policy for BI-V100
   constexpr ScanLookbackPolicy get_lookback(const hardware_capability& hw) const {
-    if (!hw.at_least(hardware_capability::vendor_t::iluvatar, 100))
-      goto fallback;
-
-    if (operation_t == op_kind_t::plus && is_primitive_accum) {
+    if (hw.at_least(hardware_capability::vendor_t::iluvatar, 100)
+        && operation_t == op_kind_t::plus && is_primitive_accum) {
       if (offset_size == 4) {
         switch (input_value_size) {
           case 1: return {bi100_lookback_1B_o4::threads, bi100_lookback_1B_o4::items,
@@ -222,6 +220,7 @@ struct policy_selector {
                           bi100_lookback_8B_o4::load_algo, bi100_lookback_8B_o4::load_mod,
                           bi100_lookback_8B_o4::store_algo, BLOCK_SCAN_WARP_SCANS,
                           bi100_lookback_8B_o4::delay};
+          default: break;
         }
       } else if (offset_size == 8) {
         switch (input_value_size) {
@@ -233,11 +232,12 @@ struct policy_selector {
                           bi100_lookback_8B_o8::load_algo, bi100_lookback_8B_o8::load_mod,
                           bi100_lookback_8B_o8::store_algo, BLOCK_SCAN_WARP_SCANS,
                           bi100_lookback_8B_o8::delay};
+          default: break;
         }
       }
     }
 
-  fallback:
+    // Fallback
     return {bi100_lookback_default::threads, bi100_lookback_default::items,
             bi100_lookback_default::load_algo, bi100_lookback_default::load_mod,
             bi100_lookback_default::store_algo, BLOCK_SCAN_WARP_SCANS,