# Summary
[summary]: #summary
This RFC proposes to integrate DNNL into TVM via BYOC framework. The drawback
of the current "Bring DNNL to TVM via DNNL JSON codegen/runtime" is analysed
and has been enhanced. Performance benefits are observed by comparing with
either MXNet-oneDNN or TVM-autos
The issue is similar to
[#7029](https://discuss.tvm.apache.org/t/attrs-not-inheriting-from-attrs/7029) .
I am not able to use `.keys()` on `tvm.relay.attrs.ArgReduceAttrs` object.
I checked in `tvm/python/relay/op/op_attrs.py` there is no python `class
ArgReduceAttrs`.
Can I create a PR re
@comaniac, I just updated this issue to move these planned PR not belong to
this solution to sperate tables to avoid confuse, please check.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issue
cc @mbs-octoml @denise-k is it possible for you guys to take over this one as
you now have the most context?
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7526#issuecomment-982090940
Here's where we've gotten to:
1. TECompiler has fully replaced CompileEngine :-)
2. te_complier_cache.cc still in pretty messy state, the cache datastructures
themselves can be simplified however we still have customers of
TECompiler::Lower etc via te_compiler.py.
3. After #9483 all backends w
Ok Mark will split out into follow up issues that go on the roadmap and we will
close this one. cc @Mousius
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7526#issuecomment-982229451
Closed #7526.
--
You are receiving this because you are subscribed to this thread.
Reply to this email directly or view it on GitHub:
https://github.com/apache/tvm/issues/7526#event-5688955755