add block_thread arg

op_builder/fused_adam.py

@@ -29,7 +29,8 @@ class FusedAdamBuilder(CUDAOpBuilder):
         return args + self.version_dependent_macros()
 
     def nvcc_args(self):
-        nvcc_flags = ['-O3'] + self.version_dependent_macros()
+        nvcc_flags = super().nvcc_args()
+        nvcc_flags += ['-O3'] + self.version_dependent_macros()
         if not self.is_rocm_pytorch():
             nvcc_flags.extend(
                 ['-allow-unsupported-compiler' if sys.platform == "win32" else '', '-lineinfo', '--use_fast_math'] +

op_builder/fused_lamb.py

@@ -29,7 +29,8 @@ class FusedLambBuilder(CUDAOpBuilder):
         return args + self.version_dependent_macros()
 
     def nvcc_args(self):
-        nvcc_flags = ['-O3'] + self.version_dependent_macros()
+        nvcc_flags = super().nvcc_args()
+        nvcc_flags += ['-O3'] + self.version_dependent_macros()
         if self.is_rocm_pytorch():
             ROCM_MAJOR, ROCM_MINOR = self.installed_rocm_version()
             nvcc_flags += ['-DROCM_VERSION_MAJOR=%s' % ROCM_MAJOR, '-DROCM_VERSION_MINOR=%s' % ROCM_MINOR]

run.sh

@@ -2,4 +2,4 @@
 export LIBRARY_PATH=/usr/local/lib:$LIBRARY_PATH
 #export DS_BUILD_VERSION=dtk22.10.1
 export LD_LIBRARY_PATH=/usr/local/lib/python3.7/site-packages/torch/lib:$LD_LIBRARY_PATH
-DS_BUILD_STRING=.dtk22.10.1.torch1.10 DS_BUILD_RANDOM_LTD=0 DS_BUILD_QUANTIZER=0 DS_BUILD_TRANSFORMER_INFERENCE=0 DS_BUILD_OPS=1 verbose=1 CXX=hipcc CC=hipcc python3 setup.py install bdist_wheel
+DS_BUILD_RANDOM_LTD=0 DS_BUILD_QUANTIZER=0 DS_BUILD_TRANSFORMER_INFERENCE=0 DS_BUILD_OPS=1 verbose=1 CXX=hipcc CC=hipcc python3 setup.py install bdist_wheel