[GitHub] [tvm] comaniac commented on a change in pull request #8808: [BYOC][TensorRT] Add TensorRT own int8 calibration support to TensorRT BYOC integration

[GitBox]

comaniac commented on a change in pull request #8808:
URL: https://github.com/apache/tvm/pull/8808#discussion_r709538959



##########
File path: src/runtime/contrib/tensorrt/tensorrt_builder.h
##########
@@ -153,6 +153,9 @@ class TensorRTBuilder {
   /*! \brief Whether to automatically convert model to 16-bit floating point 
precision. */
   bool use_fp16_;
 
+  /*! \brief whether to automatically convert model to int8 precision */

Review comment:
       IIUC, `use_int8_` is exclusive with `use_fp16_`? If so, we should 
combine them to be a single variable like `target_dtype`.

##########
File path: src/runtime/contrib/tensorrt/tensorrt_runtime.cc
##########
@@ -308,6 +370,7 @@ class TensorRTRuntime : public JSONRuntimeBase {
     helper.ReadAllFields(&reader);
     const int batch_size = GetBatchSize();
     trt_engine_cache_[std::make_pair(symbol_name_, batch_size)] = 
engine_and_context;
+    LOG(INFO) << "finished saving engine and context ... ";

Review comment:
       nit:
   ```suggestion
       LOG(INFO) << "Finished saving engine and context ... ";
   ```




-- 
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.org

For queries about this service, please contact Infrastructure at:
us...@infra.apache.org