lixiaoquan opened a new pull request #6921:
URL: https://github.com/apache/incubator-tvm/pull/6921
This PR is to fix a type inference issue:
In Following IR, meta[relay.Constant][0] is a relay.Const with type
TensorType([1, 4], "float32")
```
free_var %f: fn () -> bool;
%0 =
lixiaoquan commented on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-727827247
> I have a question. What do you mean "input's shape's second dim is
unknown"? TVM is able to compile the kernel even though the dim is a sym var.
This in_dim
lixiaoquan commented on pull request #6892:
URL: https://github.com/apache/incubator-tvm/pull/6892#issuecomment-727819544
@zhiics Could you please help merge this? Thanks
This is an automated message from the Apache Git
ggardet commented on issue #6832:
URL: https://github.com/apache/incubator-tvm/issues/6832#issuecomment-727895354
Created at
https://discuss.tvm.apache.org/t/tvm-0-7-0-tests-fail-with-check-failed-reg-nullptr-attributeerror-operator-reshape-is-not-registered/8466
merrymercy commented on a change in pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903#discussion_r524224815
##
File path: tutorials/auto_scheduler/tune_network_cuda.py
##
@@ -105,7 +105,6 @@ def get_network(name, batch_size, layout="NHWC",
tqchen commented on a change in pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903#discussion_r524291161
##
File path: python/tvm/auto_scheduler/relay_integration.py
##
@@ -34,18 +34,26 @@
def call_all_topi_funcs(mod, params, target):
-"""Call
zhiics commented on pull request #6892:
URL: https://github.com/apache/incubator-tvm/pull/6892#issuecomment-728163319
Thanks @lixiaoquan @mbrookhart @electriclilies
This is an automated message from the Apache Git Service.
zhiics merged pull request #6892:
URL: https://github.com/apache/incubator-tvm/pull/6892
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
comaniac commented on a change in pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903#discussion_r524450562
##
File path: python/tvm/auto_scheduler/relay_integration.py
##
@@ -34,18 +34,26 @@
def call_all_topi_funcs(mod, params, target):
-
tkonolige commented on a change in pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#discussion_r524456070
##
File path: src/relay/op/nn/sparse.cc
##
@@ -85,10 +117,11 @@ RELAY_REGISTER_OP("nn.sparse_dense")
)code" TVM_ADD_FILELINE)
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 3950639 [Doc] Minor improvements for auto-tuning tutorials (#6919)
add f2351fe [Relay] Add dynamic
tqchen commented on a change in pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903#discussion_r524453803
##
File path: python/tvm/auto_scheduler/relay_integration.py
##
@@ -34,18 +34,26 @@
def call_all_topi_funcs(mod, params, target):
-"""Call
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 3950639 [Doc] Minor improvements for auto-tuning tutorials (#6919)
add f2351fe [Relay] Add dynamic
TaylorZowtuk edited a comment on pull request #6909:
URL: https://github.com/apache/incubator-tvm/pull/6909#issuecomment-728307739
> How do you hit this part of the code? Generally, it means you have some
fatal errors in the code.
> It is very rare to recover from a case where you have
merrymercy commented on a change in pull request #6909:
URL: https://github.com/apache/incubator-tvm/pull/6909#discussion_r524836173
##
File path: python/tvm/auto_scheduler/auto_schedule.py
##
@@ -89,7 +89,7 @@ def __init__(
num_measure_trials=0,
tkonolige commented on pull request #6854:
URL: https://github.com/apache/incubator-tvm/pull/6854#issuecomment-728343498
@tqchen This PR is all ready to go. Is there a reviewer you could suggest?
This is an automated message
tqchen closed issue #6925:
URL: https://github.com/apache/incubator-tvm/issues/6925
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to
comaniac opened a new pull request #6927:
URL: https://github.com/apache/incubator-tvm/pull/6927
One issue of the current auto_scheduler task serialization is that the
workload won't be registered when deserializing a task so users have to
manually call `register_workload_tensors` after
alter-xp opened a new pull request #6928:
URL: https://github.com/apache/incubator-tvm/pull/6928
* segment_max, segment_min, segment_mean, segment_sum, segment_prod
* unsorted_segment_max, unsorted_segment_min, unsorted_segment_mean
* unsorted_segment_prod, unsorted_segment_sum
naokishibuya opened a new issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929
Hello,
I encountered an exception from relay with a PyTorch model that has
`nn.Sigmoid`.
To reproduce the error, the script can be used.
- The model has only one operator
TaylorZowtuk commented on pull request #6909:
URL: https://github.com/apache/incubator-tvm/pull/6909#issuecomment-728307739
> How do you hit this part of the code? Generally, it means you have some
fatal errors in the code.
> It is very rare to recover from a case where you have so many
This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from f2351fe [Relay] Add dynamic SparseToDense (#6892)
add bed621e [CI] Update actions miniconda (#6926)
comaniac commented on pull request #6926:
URL: https://github.com/apache/incubator-tvm/pull/6926#issuecomment-728381314
Thanks @tqchen @zhiics
This is an automated message from the Apache Git Service.
To respond to the
comaniac merged pull request #6926:
URL: https://github.com/apache/incubator-tvm/pull/6926
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above
MarisaKirisame commented on pull request #6921:
URL: https://github.com/apache/incubator-tvm/pull/6921#issuecomment-728671511
Can you fix the CI?
This is an automated message from the Apache Git Service.
To respond to the
masahi edited a comment on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728673244
I can reproduce the error with cuda and llvm backend. For llvm, I get
```
File "/home/masa/projects/dev/tvm/src/target/llvm/codegen_llvm.cc", line
776
zhiics merged pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from bed621e [CI] Update actions miniconda (#6926)
add e8de2c5 [AutoSchedule] Extract tasks via compile engine
zhiics commented on pull request #6903:
URL: https://github.com/apache/incubator-tvm/pull/6903#issuecomment-728674105
Thanks everyone.
This is an automated message from the Apache Git Service.
To respond to the message,
naokishibuya closed issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
naokishibuya commented on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728684676
@masahi that's a great findings! The actual model I use has `sigmoid` at
the end of the network to make the outputs in [0, 1]. So, I could call
`dequant` before the
areusch opened a new pull request #6930:
URL: https://github.com/apache/incubator-tvm/pull/6930
This commit makes an internal API change in the µTVM transport library and
which allows for some fixes to the GdbDebugger class, improving if not
unbreaking the debug flow. When timeouts were
masahi commented on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728673244
I can reproduce the error with llvm backend:
```
File "/home/masa/projects/dev/tvm/src/target/llvm/codegen_llvm.cc", line
776
TVMError:
masahi edited a comment on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728673244
I can reproduce the error with llvm backend:
```
File "/home/masa/projects/dev/tvm/src/target/llvm/codegen_llvm.cc", line
776
TVMError:
masahi commented on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728675747
@naokishibuya If I remove `quant`/`dequant`, it works. So I think it is the
problem of sigmoid applied to `uint8` type. Are you sure you want to run
sigmoid on quantized input?
masahi edited a comment on issue #6929:
URL: https://github.com/apache/incubator-tvm/issues/6929#issuecomment-728675747
@naokishibuya If I remove `quant`/`dequant`, it works. So I think it is the
problem of sigmoid applied to `uint8` type. Are you sure you want to run
sigmoid on quantized
comaniac commented on issue #6922:
URL: https://github.com/apache/incubator-tvm/issues/6922#issuecomment-728240616
Looks like we need `self.executor = LocalExecutor(timeout=self.timeout)` in
ANSHUMAN87 commented on pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#issuecomment-728244556
> But maybe someone else can chime in.
Thanks @tkonolige for your feedback. I believe the performance stats are
quite clear to opt for a new Op in the case.
bernhardklein commented on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728244254
relates to this [6924](https://github.com/apache/incubator-tvm/pull/6924)
issue.
This is an
tkonolige commented on pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#issuecomment-728249449
Sorry, I meant that I'm not sure about the using flags approach vs having a
separate operator for sparse x dense vs dense x sparse. From your benchmarks,
it does look
tqchen commented on issue #6925:
URL: https://github.com/apache/incubator-tvm/issues/6925#issuecomment-728262062
https://github.com/apache/incubator-tvm/pull/6926
This is an automated message from the Apache Git Service.
To
tqchen opened a new pull request #6926:
URL: https://github.com/apache/incubator-tvm/pull/6926
cc @comaniac
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
bernhardklein opened a new issue #6922:
URL: https://github.com/apache/incubator-tvm/issues/6922
In the [RPCRunner
class](https://github.com/apache/incubator-tvm/blob/main/python/tvm/autotvm/measure/measure.py)
the timeout is not correctly passed to the
codeislife99 opened a new pull request #6923:
URL: https://github.com/apache/incubator-tvm/pull/6923
This is a PR just to maintain parity between neo/tvm and apache/tvm.
This is an automated message from the Apache Git
bernhardklein opened a new pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924
If we hand-over the timeout to the constructor of the LocalExecutor, like
done in the LocalBuilder class it seems to solve the issue and the timeout is
now correctly passed.
bernhardklein commented on issue #6922:
URL: https://github.com/apache/incubator-tvm/issues/6922#issuecomment-728243663
I created a matching pull request
[6924](https://github.com/apache/incubator-tvm/pull/6924) for this.
We can not see it in the logs, I checked it in the logs is the
bernhardklein commented on issue #6922:
URL: https://github.com/apache/incubator-tvm/issues/6922#issuecomment-728247695
Is not readable in the logs, because for the logs self.timeout is used,
which is correct.
So with the pull request it should be ok.
ANSHUMAN87 commented on a change in pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#discussion_r524490253
##
File path: src/relay/op/nn/sparse.cc
##
@@ -85,10 +117,11 @@ RELAY_REGISTER_OP("nn.sparse_dense")
)code" TVM_ADD_FILELINE)
comaniac opened a new issue #6925:
URL: https://github.com/apache/incubator-tvm/issues/6925
According to the error message [1] and Github announcement [2], Github
Actions now forbids commands such as `add-path` or `set-env` that changes the
system environment for the security concern
comaniac commented on issue #6925:
URL: https://github.com/apache/incubator-tvm/issues/6925#issuecomment-728251960
Blocking #6903, #6923, #6924
This is an automated message from the Apache Git Service.
To respond to the
tkonolige commented on a change in pull request #6889:
URL: https://github.com/apache/incubator-tvm/pull/6889#discussion_r524495292
##
File path: src/relay/op/nn/sparse.cc
##
@@ -85,10 +117,11 @@ RELAY_REGISTER_OP("nn.sparse_dense")
)code" TVM_ADD_FILELINE)
51 matches
Mail list logo