This is pretty cool, thanks a lot for the detailed explanation.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rpc-related-whats-the-difference-between-rpc-proxy-rpc-server-rpc-tracker/3054/4)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe fr
Does the library module of Executable cannot use the system library module or
it's useless?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/relay-why-the-relay-vm-has-no-system-lib-bool-or-runtime-tvm-runtime-runtime-options-to-build/15204/1)
to respond.
You are receiving this because
 
The module is doing *Linear* transform, and i dispatch it to pre-scheduled op
in MLC-LLM dolly-v2-3b.
I profile i
I tried BYOC
followed
https://tvm.apache.org/docs/dev/how_to/relay_bring_your_own_codegen.html ,and
registered function to TVM backend. But how do I check this result and generate
C code as example?
I use
> f1 = tvm.get_global_func("relay.ext.ccompiler")
and it runs normally, but how d
tir.const should be used when we want to represent a constant immediate. We do
not recommend `alloc_const` was used to create an allocation that associates
with some constant array.
Although we do not recommend using it, since it is not compatible with many tir
schedules. Instead, we encoura
Thanks a lot. @tqchen Really appreciate it!
---
[Visit
Topic](https://discuss.tvm.apache.org/t/what-is-the-difference-between-tvm-tir-const-and-ir-builder-allocate-const-in-tvm-graph-construction-using-tir/15199/3)
to respond.
You are receiving this because you enabled mailing list mode.
I have two interpolate ops defined in PyTorch that take a (10, 10, 128) tensor
and convert it to a (20, 20, 128) op as follows: (10,10,128) -> (10, 20, 128)
-> (20, 20, 128).
The corresponding Relay ops are incorrectly interpreted as:
(10, 10, 128) -> (10, 10, 128) -> (19, 19, 128).
Looking
