I would like to propose one thing that we need to consider whether this
platform have mobile apps or not; Another thing is whether this platform is
good to access from anywhere. For example, in China, it is not all platforms
can be accessed. :slight_smile:
---
[Visit
Topic](https://disc
Thanks for sharing this information. @tqchen How do we avoid this condition in
the future? Doc tutorial doesn't exist in CI but it is very important, but
developers forget to update it very easily.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/the-tvm-developers-should-update-your-tu
For the F1, current design is simply to add multi model support (in the
previous pr I even implemented draft multi model support to verify current
design) , even on different ctxs. But the issue is the unique compiled name as
@tqchen described, we could evaluate and discuss whether we should d
One question for the performance regression, how to judge the normal
fluctuation, especially CPU? Like resnet50 maybe 20.00ms, but becomes 20.88ms
after one pr?
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-building-a-new-reproducible-benchmark-for-tvm/8496/7)
to respond.
You
I enjoy the reading of https://arxiv.org/abs/2006.03031 which supports dyn
model support in the TVM using relay vm.
However, i want to ask some quick questions:
1. Do we have uploaded completely of Nimble code on the mainstream? Especially
about the memory performance issue like this :
https
I would like to add one `flags` attribute to make us have more extension for
the future. Like we could have `Span: (sourcename: ..., line:... column:...
flags: SPFlagSourceNameImportedFromModel, ...)` Then we could query the flags
attribute to handle the specific condition.
---
[Visit
To
Ah...u are right, @giuseros sorry i mislead u. I remembered wrong before. We
will have one default value, it is 1 if i remember correctly. But even we could
have one value, the value is not trusted, because we haven’t tuned it. We maybe
could say we could fix it for 4 or 8, but I think it does
[quote="giuseros, post:11, topic:8253"]
What I am missing is why we don’t want to change the layout when
`cfg.is_fallback` . In that case, the strategy is defined
[/quote]
When we enter into fall back configuration means we don't find the
configuration of this workload in the tuning log. So li
For alter_op_layout, we will alter the weight layout, normally we will change
the weight layout to 5D, the last dim is queried from our AutoTVM log file. For
example:
```
if topi_tmpl == "conv2d_nchw_spatial_pack.arm_cpu":
assert data_layout == "NCHW" and kernel_layout == "OIHW"
@giuseros @anijain2305 Let us accept one more argument like `alter_op_layout`
```
@tvm.target.generic_func
def conv2d_alter_layout(attrs, inputs, tinfos, out_type):
@tvm.target.generic_func
def qnn_conv2d_legalize(attrs, inputs, types):
"""Default legalization is None."""
return None
@giuseros I doesn't run it, but according to my understanding, these two
functions's inputs should be the same type (tvm.relay.expr). For example,
inside the alter_op_layout function we have logic:
```
# HWIO -> OIHW
kernel_transform = relay.transpose(inputs[1], axes=[3, 2, 0, 1])
# alpha, al
Looking forward it. TVM auto scheduler is also doing some experiment on this. I
believe spare network has a good future too.
---
[Visit Topic](https://discuss.tvm.apache.org/t/discuss-tvm-v0-8-roadmap/8139/8)
to respond.
You are receiving this because you enabled mailing list mode.
To un
[quote="giuseros, post:1, topic:8253"]
`qnn_conv2d_legalize.register`
[/quote]
does code in `alter_op_layout` work?
```
best_plevel_impl, outs = relay.backend.compile_engine.select_implementation(
relay.op.get("nn.conv2d"), attrs, tinfos, out_type, target)
if best_plevel_impl.nam
I think we could just send pr directly. Of course, we could make them be
several prs, not one big pr.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/add-some-new-tensorflow-ops/8217/3) to
respond.
You are receiving this because you enabled mailing list mode.
To unsubscribe from thes
My code review is what TQ said. When we call `export_library`, we could save
`a.tar` or `a.so`. If we save `a.tar`, which contains the object file (like
a.o), this is different with `tvmc`'s `tar` collections.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/rfc-optionally-include-objec
If you want to measure it more robust, you should run it more times and
calculate its average time. For example you could run 1000 times.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/strassen-algorithm-for-dense/2661/16)
to respond.
You are receiving this because you enabled mailin
On your case, current code is will call 4 cores (id 0 ~ 3). So parallel brings
you better performance.
About time consuming functions, Do you use auto tvm? If you use auto tvm, the
default cpu TVM uses is big core (that is index 7). If you decide to use 4
little cores, you should make auto tv
I don't think u should set `TVM_NUM_THREADS` on arm because of arm's BIG LITTLE
architecture. I think you should call `runtime.config_thread_pool` to complete
the core binding work. Another thing is we shouldn't make tvm worker thread run
different frequency cpus (aka, one worker thread is in
@jcf94 has explained very well for strassen algorithm. The link you posted is I
wrote. However, we should notice that my post is not to show the best
performance TVM could achieve, just show how easy TVM could a reasonable
performance (beyond numpy).
If we still want to improve performance,
The performance can not beyond dense would have many reasons, but I think
strassen algorithm is not one key part. @jcf94 has done some experiment on this.
---
[Visit
Topic](https://discuss.tvm.apache.org/t/strassen-algorithm-for-dense/2661/6) to
respond.
You are receiving this because yo
20 matches
Mail list logo
