Fix build error from PR pytorch#782

Author: zsef123

cpp/bin/torchtrtc/main.cpp

@@ -229,8 +229,6 @@ int main(int argc, char** argv) {
 
   args::Flag build_debuggable_engine(
       parser, "build-debuggable-engine", "Creates a debuggable engine", {"build-debuggable-engine"});
-  args::Flag use_strict_types(
-      parser, "use-strict-types", "Restrict operating type to only use set operation precision", {"use-strict-types"});
   args::Flag allow_gpu_fallback(
       parser,
       "allow-gpu-fallback",
@@ -306,8 +304,6 @@ int main(int argc, char** argv) {
       parser, "num_iters", "Number of averaging timing iterations used to select kernels", {"num-avg-timing-iters"});
   args::ValueFlag<uint64_t> workspace_size(
       parser, "workspace_size", "Maximum size of workspace given to TensorRT", {"workspace-size"});
-  args::ValueFlag<uint64_t> max_batch_size(
-      parser, "max_batch_size", "Maximum batch size (must be >= 1 to be set, 0 means not set)", {"max-batch-size"});
   args::ValueFlag<double> threshold(
       parser,
       "threshold",
@@ -460,10 +456,6 @@ int main(int argc, char** argv) {
     compile_settings.debug = true;
   }
 
-  if (use_strict_types) {
-    compile_settings.strict_types = true;
-  }
-
   if (allow_gpu_fallback) {
     compile_settings.device.allow_gpu_fallback = true;
   }
@@ -586,10 +578,6 @@ int main(int argc, char** argv) {
     compile_settings.workspace_size = args::get(workspace_size);
   }
 
-  if (max_batch_size) {
-    compile_settings.max_batch_size = args::get(max_batch_size);
-  }
-
   if (truncate_long_and_double) {
     compile_settings.truncate_long_and_double = true;
   }

py/torch_tensorrt/ts/_compiler.py

@@ -17,7 +17,6 @@ def compile(module: torch.jit.ScriptModule,
             enabled_precisions=set(),
             refit=False,
             debug=False,
-            strict_types=False,
             capability=_enums.EngineCapability.default,
             num_min_timing_iters=2,
             num_avg_timing_iters=1,
@@ -65,7 +64,6 @@ def compile(module: torch.jit.ScriptModule,
         enabled_precision (Set(Union(torch.dtype, torch_tensorrt.dtype))): The set of datatypes that TensorRT can use when selecting kernels
         refit (bool): Enable refitting
         debug (bool): Enable debuggable engine
-        strict_types (bool): Kernels should strictly run in a particular operating precision. Enabled precision should only have one type in the set
         capability (torch_tensorrt.EngineCapability): Restrict kernel selection to safe gpu kernels or safe dla kernels
         num_min_timing_iters (int): Number of minimization timing iterations used to select kernels
         num_avg_timing_iters (int): Number of averaging timing iterations used to select kernels
@@ -98,7 +96,6 @@ def compile(module: torch.jit.ScriptModule,
         "enabled_precisions": enabled_precisions,  # Enabling FP16 kernels
         "refit": refit,  # enable refit
         "debug": debug,  # enable debuggable engine
-        "strict_types": strict_types,  # kernels should strictly run in operating precision
         "capability": capability,  # Restrict kernel selection to safe gpu kernels or safe dla kernels
         "num_min_timing_iters": num_min_timing_iters,  # Number of minimization timing iterations used to select kernels
         "num_avg_timing_iters": num_avg_timing_iters,  # Number of averaging timing iterations used to select kernels
@@ -127,7 +124,6 @@ def convert_method_to_trt_engine(module: torch.jit.ScriptModule,
                                  enabled_precisions=set(),
                                  refit=False,
                                  debug=False,
-                                 strict_types=False,
                                  capability=_enums.EngineCapability.default,
                                  num_min_timing_iters=2,
                                  num_avg_timing_iters=1,
@@ -169,7 +165,6 @@ def convert_method_to_trt_engine(module: torch.jit.ScriptModule,
         enabled_precision (Set(Union(torch.dtype, torch_tensorrt.dtype))): The set of datatypes that TensorRT can use when selecting kernels
         refit (bool): Enable refitting
         debug (bool): Enable debuggable engine
-        strict_types (bool): Kernels should strictly run in a particular operating precision. Enabled precision should only have one type in the set
         capability (torch_tensorrt.EngineCapability): Restrict kernel selection to safe gpu kernels or safe dla kernels
         num_min_timing_iters (int): Number of minimization timing iterations used to select kernels
         num_avg_timing_iters (int): Number of averaging timing iterations used to select kernels
@@ -193,7 +188,6 @@ def convert_method_to_trt_engine(module: torch.jit.ScriptModule,
         "enabled_precisions": enabled_precisions,  # Enabling FP16 kernels
         "refit": refit,  # enable refit
         "debug": debug,  # enable debuggable engine
-        "strict_types": strict_types,  # kernels should strictly run in operating precision
         "capability": capability,  # Restrict kernel selection to safe gpu kernels or safe dla kernels
         "num_min_timing_iters": num_min_timing_iters,  # Number of minimization timing iterations used to select kernels
         "num_avg_timing_iters": num_avg_timing_iters,  # Number of averaging timing iterations used to select kernels