[Bugfix] Fix a bug when simplifying warp combination for T.gemm (tile-ai#540)

Author: LeiWang1999

src/op/gemm.cc

@@ -194,10 +194,6 @@ std::pair<int, int> Gemm::ComputeWarpPartition(int num_warps, Target target,
     // Try all possible combinations that satisfy the constraints
     for (int m = 1; m <= max_m_warps && m <= num_warps; m++) {
       int n = num_warps / m;
-      if (n > max_n_warps)
-        continue;
-      if (m * n != num_warps)
-        continue;
 
       // Calculate how balanced this partition is
       float m_per_warp = static_cast<float>(this->M) / (m * kMPerWarp);

tilelang/jit/__init__.py

@@ -179,6 +179,9 @@ def wrapper(*args: _P.args, **kwargs: _P.kwargs) -> Any:
                 else:
                     raise ValueError(f"Invalid function type: {type(program_result_source)}")
 
+                if self.verbose:
+                    logger.info(f"Verbose: Compiling for program \n {program_result.script()}")
+
                 kernel_result = compile(
                     program_result,
                     out_idx=self.out_idx,