Remove unnecessary pass configurations for warp specialization and TMA lowering in fast math operation tests for CUDA. This simplifies the test setup while maintaining the focus on fast math functionality.

Author: LeiWang1999

testing/python/fastmath/test_mathops_fastmath.py

@@ -79,8 +79,6 @@ def main(
         out_idx=[1],
         target="cuda",
         pass_configs={
-            tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
-            tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
             tilelang.PassConfigKey.TL_ENABLE_FAST_MATH: False,
         })
 
@@ -124,8 +122,6 @@ def main(
         out_idx=[2],
         target="cuda",
         pass_configs={
-            tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
-            tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
             tilelang.PassConfigKey.TL_ENABLE_FAST_MATH: False,
         })
 
@@ -135,8 +131,6 @@ def main(
         out_idx=[2],
         target="cuda",
         pass_configs={
-            tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
-            tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
             tilelang.PassConfigKey.TL_ENABLE_FAST_MATH: True,
         })
 
@@ -232,8 +226,6 @@ def main(
         out_idx=[1],
         target="cuda",
         pass_configs={
-            tilelang.PassConfigKey.TL_DISABLE_WARP_SPECIALIZED: True,
-            tilelang.PassConfigKey.TL_DISABLE_TMA_LOWER: True,
             tilelang.PassConfigKey.TL_ENABLE_FAST_MATH: True,
         })