se latest thread here
https://discuss.tvm.ai/t/performing-relay-passes-non-recursively/5696 the
initial version of non-recursive visitor is already upstreamed
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-discuss-non-recursive-ast-visiting/2481/5)
to respond.
You are receiving this bec
https://github.com/apache/incubator-tvm/pull/4886
---
[Visit
Topic](https://discuss.tvm.ai/t/performing-relay-passes-non-recursively/5696/22)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https://discuss.tvm.ai/e
TVM stack uses the PackedFunc and TypedPackedFun extensively to expose
functions to the frontend. They serve as a foundation of the runtime system and
FFI.
A PackedFunc call passes an ObjectRef type by the pointer value of the internal
object pointer. The corresponding `Object*` values can b
Hi,
Our team is developing Relay to ONNX conversion program which currently​
contains 66 operators.
You can take our program for reference.
This is the hyperlink to [source
code](https://github.com/itri-tvm/Relay2ONNX/tree/master/python/tvm/relay/frontend)
and [example
code](https://githu
These suggestion all makes sense. I think we should bring relay to ONNX
support. The only choices we need to discuss so far are:
- C0: put the onnx under the export namespace, which could imply that it is a
serialization format(and all of relay can serialize to it).
- C1: put the onnx under `t
POC https://github.com/apache/incubator-tvm/pull/5271
---
[Visit
Topic](https://discuss.tvm.ai/t/rfc-support-rvalue-reference-passing-in-typedpackedfunc/6264/2)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from these emails, [click
here](https
