I am a newer to TVM, from my point, compute + schedule + auto tuning convert
the relay IR to Tensor IR.
this process includes many hardware special optimizations related with schedule
primitives. After the auto tuning, Tensor IR was generated.
Q1: Besides the AutoTVM(include schedules), what
Hi guys, I'm new to TVM and I was trying to test the performance of a single
operator on NVGPU.
So far I found the doc about how to test model
benchmark(https://github.com/apache/incubator-tvm/blob/main/apps/benchmark/README.md).
And the doc about [Tuning High Performance Convolution on NVIDIA
Hi developers：
How can I add the new quantization method for TVM? Or is there a tutorial ?
The community experts could help to clarify the question? I would highly
appreciate your response.
Thanks a lot!
Best Regards, Fred
---
[Visit
Topic](https://discuss.tvm.apache.org/t/quantization
I'm no expert with this, but if you take a look in build_module.py, you can see
what TIR passes are run after the schedules have been lowered. I'll paste them
here for convenience:
```
tvm.tir.transform.InjectPrefetch(),
tvm.tir.transform.StorageFlatten(64, instrument_bound_checkers),
tvm.tir.t
I am working on the new quantization framework right now -- it is currently in
progress.
Our rough timeline is an RFC in three weeks to a month from now, and then
upstreaming the finalized quantization framework in the two weeks after that.
It would be great to get your feedback on the final
What @matt-arm pointed out is correct. In addition, your figure is not exactly
correct. relay.build actually goes the same flow as AutoTVM/TE schedule. When
calling relay.build, it lowers each operator to TE according to Relay op
strategy. The op strategy will select a TE compute/schedule for
@mbrookhart So I tried the way you suggested and I'm able to rewrite the
pattern inside a function. I wonder if it's also possible to partition and
rewrite a pattern across multiple functions? I suspect if this would need the
support of the potential `FunctionPattern`.
---
[Visit
Topic](
Like a pattern that exists across multiple functions? Yes, we'll need a
FunctionPattern.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/how-to-match-the-pattern-of-a-function-in-relay/8283/21)
to respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe f
Hi electriclilies, I'm glad to hear that! It will be gorgeous if the new
quantization framework is easy to add new methods. Noteworthily, the quantize
method depends on the graph structure.
Thanks a lot.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/quantization-how-to-add-new-quanti
