FrozenGene commented on a change in pull request #8808:
URL: https://github.com/apache/tvm/pull/8808#discussion_r696234249
##########
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:
Another way is we could accept both options. For deployment @ edge
devices (but compile model @ server), if we could reduce the usage of
environment values, we could make deployment easier. However, if users set
environment value , which has higher priority and will override compilation
setting, as they know what they are doing. @trevor-m @jcf94
--
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]
