This is a tricky question. Theoretically you only need to build the module 
again without `apply_history_best` and measure its latency. However, if you 
build the same module twice, the compiler engine will use the previous built 
programs to reduce the build time in the second time. This can be resolved by 
adding the following lines:

```python
from tvm.relay.backend import compile_engine
...
compile_engine.get().clear()
with apply_history_best(...):
  graph, lib, params = relay.build_module.build(mod, target=target, 
params=params)
runtime1 = graph_runtime.create(graph, lib, dev_ctx)

compile_engine.get().clear()
graph, lib, params = relay.build_module.build(mod, target=target, params=params)
runtime2 = graph_runtime.create(graph, lib, dev_ctx)
```

The whole idea is to clean the cache in compiler engine and make sure it builds 
the module from scratch.





---
[Visit 
Topic](https://discuss.tvm.ai/t/how-to-reset-relay-to-use-the-default-config/6642/2)
 to respond.

You are receiving this because you enabled mailing list mode.

To unsubscribe from these emails, [click 
here](https://discuss.tvm.ai/email/unsubscribe/4f503e225a9048043ab89fc80dfed35c356a7d37fe26338e74ae4c6987d47bbd).

Reply via email to