tkonolige commented on code in PR #13470:
URL: https://github.com/apache/tvm/pull/13470#discussion_r1061020407
##########
python/tvm/meta_schedule/relay_integration.py:
##########
@@ -390,16 +353,20 @@ def compile_relay(
from tvm import relay
# pylint: enable=import-outside-toplevel
- mod, target, params, pass_config, executor = _normalize_params(
- mod, target, params, pass_config, executor
- )
+ mod, target, params, executor = _normalize_params(mod, target, params,
executor)
+ pass_ctx = transform.PassContext.current()
+ pass_config = dict(pass_ctx.config)
Review Comment:
Right now there is no way to determine whether or not if the current pass
context is the default or not. It might be possible to add though.
I is not consistent with the rest of TVM to default the opt_level to 3 in
meta schedule. Everywhere else defaults to 2. This does mean that we might
break some user scripts.
##########
python/tvm/meta_schedule/relay_integration.py:
##########
@@ -390,16 +353,20 @@ def compile_relay(
from tvm import relay
# pylint: enable=import-outside-toplevel
- mod, target, params, pass_config, executor = _normalize_params(
- mod, target, params, pass_config, executor
- )
+ mod, target, params, executor = _normalize_params(mod, target, params,
executor)
+ pass_ctx = transform.PassContext.current()
+ pass_config = dict(pass_ctx.config)
Review Comment:
Right now there is no way to determine whether or not if the current pass
context is the default or not. It might be possible to add though.
It is not consistent with the rest of TVM to default the opt_level to 3 in
meta schedule. Everywhere else defaults to 2. This does mean that we might
break some user scripts.
--
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]
