tiandiao123 commented on a change in pull request #8808:
URL: https://github.com/apache/tvm/pull/8808#discussion_r696938232
##########
File path: src/runtime/contrib/tensorrt/tensorrt_runtime.cc
##########
@@ -66,7 +78,16 @@ class TensorRTRuntime : public JSONRuntimeBase {
use_implicit_batch_(true),
max_workspace_size_(size_t(1) << 30),
max_batch_size_(-1),
- multi_engine_mode_(false) {}
+ multi_engine_mode_(false) {
+ const bool use_int8 = dmlc::GetEnv("TVM_TENSORRT_USE_INT8", false);
Review comment:
Hi @FrozenGene @trevor-m @jcf94 I am wondering which plan we need to
adopt? Are we going to keep environment variables, or we are going to transfer
fp16 and int8 flag into partition_for_tensorrt api?
--
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: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
