codeislife99 opened a new pull request #6784:
URL: https://github.com/apache/incubator-tvm/pull/6784
Pytorch has versions like 1.5.x+cu1XX which cause bugs in version comparison
checks. This PR fixes that.
This is an automa
codeislife99 commented on pull request #6784:
URL: https://github.com/apache/incubator-tvm/pull/6784#issuecomment-717781799
cc: @anijain2305 @zhiics @masahi
This is an automated message from the Apache Git Service.
To respon
leandron commented on a change in pull request #6781:
URL: https://github.com/apache/incubator-tvm/pull/6781#discussion_r513259984
##
File path: docker/Dockerfile.ci_arm
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor lic
leandron commented on a change in pull request #6781:
URL: https://github.com/apache/incubator-tvm/pull/6781#discussion_r513261920
##
File path: docker/Dockerfile.ci_arm
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor lic
Presburger opened a new pull request #6785:
URL: https://github.com/apache/incubator-tvm/pull/6785
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the pull request is submitted, please request code r
d-smirnov opened a new pull request #6786:
URL: https://github.com/apache/incubator-tvm/pull/6786
This PR changes signature of `FTVMAnnotateTarget` to
`runtime::TypedPackedFunc`
which allows to utilise extra information (e.g. an operation output type)
from passed expr argument.
--
mbaret commented on a change in pull request #6711:
URL: https://github.com/apache/incubator-tvm/pull/6711#discussion_r513341812
##
File path: python/tvm/topi/arm_cpu/depthwise_conv2d.py
##
@@ -298,24 +299,29 @@ def schedule_depthwise_conv2d_nhwc(cfg, outs):
cfg["tile_
giuseros commented on pull request #6675:
URL: https://github.com/apache/incubator-tvm/pull/6675#issuecomment-717882594
Hi @anijain2305 ,
LGTM, that's brilliant thanks!
This is an automated message from the Apache Git Se
giuseros commented on a change in pull request #6783:
URL: https://github.com/apache/incubator-tvm/pull/6783#discussion_r513384321
##
File path: python/tvm/relay/frontend/tensorflow.py
##
@@ -788,6 +788,14 @@ def _impl(inputs, attr, params, mod):
return _impl
+def _exp
Presburger commented on pull request #6785:
URL: https://github.com/apache/incubator-tvm/pull/6785#issuecomment-717884931
OK, @leandron
I find a IR look like this before Loop Partition.
```cc
for(i1: int32, 0, 36){
attr [IterVar(x.inner, (nullptr), "DataPar", "")]{
fo
tqchen commented on pull request #6785:
URL: https://github.com/apache/incubator-tvm/pull/6785#issuecomment-717915855
Thanks @Presburger ! It would be awesome to add a testcase to cover the
problem
This is an automated messa
tqchen edited a comment on pull request #6785:
URL: https://github.com/apache/incubator-tvm/pull/6785#issuecomment-717915855
Thanks @Presburger ! It would be awesome to add a unit testcase(e.g. use the
tir API to construct the loops then call the convertSSA) to cover the problem
-
tqchen merged pull request #6771:
URL: https://github.com/apache/incubator-tvm/pull/6771
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 g
tqchen commented on pull request #6771:
URL: https://github.com/apache/incubator-tvm/pull/6771#issuecomment-717918825
I see, in this particular case, perhaps it makes sense to optimize such
pattern and make sure `cast(i32, c * 2 + 1) + 1 - cast(i32, c * 2)` get
simplified as well. One way
tqchen closed issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691
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
masahi merged pull request #6784:
URL: https://github.com/apache/incubator-tvm/pull/6784
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 g
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 3d624ec Scatter on Cuda (#6533)
add b4858d4 [ARITH] Tight bound for floormod (#6771)
No new revisions we
masahi commented on pull request #6784:
URL: https://github.com/apache/incubator-tvm/pull/6784#issuecomment-717919410
Thanks @codeislife99
This is an automated message from the Apache Git Service.
To respond to the message,
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from b4858d4 [ARITH] Tight bound for floormod (#6771)
add 99027fc Fix version check bug (#6784)
No new revisi
tqchen commented on pull request #6771:
URL: https://github.com/apache/incubator-tvm/pull/6771#issuecomment-717920381
THanks @hzfan @giuseros . It would also be great if we can followup further
on the above case:
- Find out why cast i32 is inserted (ideally we should be all in i64 in
BhushanIMG commented on a change in pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477#discussion_r513479979
##
File path: include/tvm/topi/nn.h
##
@@ -459,6 +460,178 @@ inline tvm::te::Tensor group_conv2d_ngchw(const
tvm::te::Tensor& I, const tvm::t
BhushanIMG commented on a change in pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477#discussion_r513479696
##
File path: include/tvm/topi/nn.h
##
@@ -459,6 +460,178 @@ inline tvm::te::Tensor group_conv2d_ngchw(const
tvm::te::Tensor& I, const tvm::t
BhushanIMG commented on a change in pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477#discussion_r513480331
##
File path: python/tvm/topi/testing/space_to_batch_nd.py
##
@@ -0,0 +1,90 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# o
mbaret commented on pull request #6787:
URL: https://github.com/apache/incubator-tvm/pull/6787#issuecomment-718020057
cc @tqchen @zhiics
This is an automated message from the Apache Git Service.
To respond to the message, pl
mbaret opened a new pull request #6787:
URL: https://github.com/apache/incubator-tvm/pull/6787
This is useful for unregistering functions after a test. Needed to resolve a
CI issue I'm experienced in https://github.com/apache/incubator-tvm/pull/6697.
--
zhiics commented on a change in pull request #6781:
URL: https://github.com/apache/incubator-tvm/pull/6781#discussion_r513567899
##
File path: docker/Dockerfile.ci_arm
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor licen
zhiics commented on a change in pull request #6781:
URL: https://github.com/apache/incubator-tvm/pull/6781#discussion_r513569364
##
File path: docker/Dockerfile.ci_arm
##
@@ -0,0 +1,44 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor licen
tqchen commented on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-718038395
Fixed by #6771. However, it will still be great to followup on this case
This is an automated message from the A
tqchen edited a comment on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-718038395
This can be resolved by #6771. However, it will still be great to followup
on this case of why cast i32 is inserted and we should work to simplify that
case
---
tqchen edited a comment on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-718038395
This can be resolved by #6771. thanks @hzfan .
However, it will still be great to followup on this case of why cast i32 is
inserted and we should work to simplify t
trevor-m commented on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-718051523
Thanks @hzfan and @tqchen for the help!
This is an automated message from the Apache Git Service.
To respond t
leandron opened a new pull request #6788:
URL: https://github.com/apache/incubator-tvm/pull/6788
This solves a `TODO` item on TVMC, using a common function to obtain the
target from `--target` in the command line. The common function is already used
in `tvmc tune`.
cc @comaniac @Fro
tkonolige commented on pull request #6671:
URL: https://github.com/apache/incubator-tvm/pull/6671#issuecomment-718075660
Maybe we should at least leave a comment that they are broken when using the
spawn method?
This is
rohanmukh commented on a change in pull request #6776:
URL: https://github.com/apache/incubator-tvm/pull/6776#discussion_r513623481
##
File path: tests/python/relay/test_vm.py
##
@@ -754,5 +754,21 @@ def test_vm_reshape_tensor():
check_result([x_np, y_np], x_np.reshape([8,
anijain2305 commented on pull request #6675:
URL: https://github.com/apache/incubator-tvm/pull/6675#issuecomment-718125768
@ZihengJiang @u99127 Can you please take a look again? PR changed after I
incorporated @giuseros comments.
---
areusch opened a new pull request #6789:
URL: https://github.com/apache/incubator-tvm/pull/6789
This PR adds a pyserial transport to µTVM, allowing it to be used with
physical hardware attached to the machine. This splits #6703 in half and adds
just the zephyr-specific runtime components.
tqchen merged pull request #6787:
URL: https://github.com/apache/incubator-tvm/pull/6787
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 g
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new ad92efd [API] Added remove_global_func to th
tkonolige opened a new pull request #6790:
URL: https://github.com/apache/incubator-tvm/pull/6790
Like #6671 this PR fixes autotvm when using the spawn start method for
multiprocessing. I've added some tests to make sure that things work with spawn
in the CI. I've also added notices to the
areusch commented on pull request #6789:
URL: https://github.com/apache/incubator-tvm/pull/6789#issuecomment-718173898
cc @tmoreau89 @tqchen @u99127 @manupa-arm @leandron @tom-gall @liangfu
@mshawcroft
This is an automated m
anijain2305 commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513723931
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
anijain2305 merged pull request #6776:
URL: https://github.com/apache/incubator-tvm/pull/6776
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
anijain2305 commented on pull request #6776:
URL: https://github.com/apache/incubator-tvm/pull/6776#issuecomment-718191989
Thanks @rohanmukh @altanh @icemelon9
This is merged
This is an automated message from the Apache G
tom-gall commented on a change in pull request #6789:
URL: https://github.com/apache/incubator-tvm/pull/6789#discussion_r513742956
##
File path: python/tvm/target/target.py
##
@@ -220,19 +220,24 @@ def intel_graphics(model="unknown", options=None):
return Target(" ".join([
This is an automated email from the ASF dual-hosted git repository.
anijain2305 pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from ad92efd [API] Added remove_global_func to the Python API (#6787)
add 4c4888b [ManifestAlloc] Handle
gussmith23 edited a comment on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718198239
```
error: failed to run custom build command for `tvm-sys v0.1.0
(https://github.com/apache/incubator-tvm?branch=main#4c4888bc)`
Caused by:
proces
gussmith23 commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718198239
```
error: failed to run custom build command for `tvm-sys v0.1.0
(https://github.com/apache/incubator-tvm?branch=main#4c4888bc)`
Caused by:
process didn'
tkonolige edited a comment on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718200850
Have you tried specifying `LLVM_CONFIG_PATH` to point to your llvm install?
This is an automated
tkonolige commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718200850
Have you tried specifying `LLVM_CONFIG_PATH`?
This is an automated message from the Apache Git Service.
This is an automated email from the ASF dual-hosted git repository.
zhic pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/ci-docker-staging by this push:
new 19b4fc3 [CI] Add m6g
tqchen commented on pull request #6373:
URL: https://github.com/apache/incubator-tvm/pull/6373#issuecomment-718216131
ping @Laurawly @icemelon9 please follow up
This is an automated message from the Apache Git Service.
To res
tqchen commented on pull request #6191:
URL: https://github.com/apache/incubator-tvm/pull/6191#issuecomment-718216353
@zhanghaohit please rebase and we can merge
This is an automated message from the Apache Git Service.
To re
tqchen commented on pull request #6344:
URL: https://github.com/apache/incubator-tvm/pull/6344#issuecomment-718216813
closing for now as per inactive status, feel free to reopen a new one
This is an automated message from the
tqchen commented on pull request #6370:
URL: https://github.com/apache/incubator-tvm/pull/6370#issuecomment-718217069
@yzhliu @hanke580 please followup :)
This is an automated message from the Apache Git Service.
To respond t
zhiics commented on a change in pull request #6373:
URL: https://github.com/apache/incubator-tvm/pull/6373#discussion_r513786300
##
File path: tests/python/relay/test_any.py
##
@@ -891,6 +891,87 @@ def test_any_ndarray_size():
verify_any_ndarray_size((2, 2))
verify_an
tqchen closed pull request #6344:
URL: https://github.com/apache/incubator-tvm/pull/6344
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 g
gussmith23 commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718217093
Yes, it's set! I think I was getting a different error before I realized I
needed to set that.
This is
tqchen commented on pull request #6774:
URL: https://github.com/apache/incubator-tvm/pull/6774#issuecomment-718217901
@leandron please confirm if it fixes your problem and we can proceed with a
merge versus revert
This is an
tqchen closed pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765
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 g
tqchen commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718218179
Closing, glad that the problem is resolved
This is an automated message from the Apache Git Service.
To res
tqchen merged pull request #6767:
URL: https://github.com/apache/incubator-tvm/pull/6767
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 g
masahi commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513771153
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
+
tqchen commented on pull request #6767:
URL: https://github.com/apache/incubator-tvm/pull/6767#issuecomment-718218947
merging per reviews, feel free to send followup improvements per
@MarisaKirisame 's comment
Thanks @jroesch @altanh @antinucleon @MarisaKirisame
--
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 4c4888b [ManifestAlloc] Handle TupleType inputs in CheckReshapeOnly
(#6776)
add 39cd612 [Relay][Training
masahi commented on pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#issuecomment-718220692
> Overall looks good. Is this enough to run qBERT? I am surprised that we
dont need to work on requantize here
Yes this is enough. Dynamic quantization flow replaces
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 4c4888b [ManifestAlloc] Handle TupleType inputs in CheckReshapeOnly
(#6776)
add 39cd612 [Relay][Training
areusch commented on a change in pull request #6789:
URL: https://github.com/apache/incubator-tvm/pull/6789#discussion_r513774283
##
File path: python/tvm/target/target.py
##
@@ -220,19 +220,24 @@ def intel_graphics(model="unknown", options=None):
return Target(" ".join(["
Laurawly commented on a change in pull request #6373:
URL: https://github.com/apache/incubator-tvm/pull/6373#discussion_r513774175
##
File path: python/tvm/relay/op/image/_image.py
##
@@ -109,6 +136,23 @@ def compute_affine_grid(attrs, inputs, out_dtype):
reg.register_inject
anijain2305 commented on pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#issuecomment-718221534
> > Overall looks good. Is this enough to run qBERT? I am surprised that we
dont need to work on requantize here
>
> Yes this is enough. Dynamic quantization flo
Laurawly commented on a change in pull request #6373:
URL: https://github.com/apache/incubator-tvm/pull/6373#discussion_r513774407
##
File path: python/tvm/relay/op/image/_image.py
##
@@ -118,3 +162,19 @@ def compute_grid_sample(attrs, inputs, out_dtype):
return [topi.imag
anijain2305 edited a comment on pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#issuecomment-718221534
> > Overall looks good. Is this enough to run qBERT? I am surprised that we
dont need to work on requantize here
>
> Yes this is enough. Dynamic quantizat
masahi commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513790693
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
+
anijain2305 commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513775161
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
masahi commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513775708
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
+
anijain2305 commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r51365
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
masahi commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513778997
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
+
masahi commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513778997
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
+
anijain2305 commented on a change in pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#discussion_r513780334
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -826,6 +826,74 @@ def _impl(inputs, _):
return _impl
+def _linear_dynamic():
zhiics merged pull request #6781:
URL: https://github.com/apache/incubator-tvm/pull/6781
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 g
gussmith23 commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718262036
Oops, this problem isn't resolved! Sorry, didn't mean to imply that. I had
already set `LLVM_CONFIG_PATH` before getting this error.
--
tqchen commented on pull request #6765:
URL: https://github.com/apache/incubator-tvm/pull/6765#issuecomment-718264432
In this case it is indeed versy strange that stddef is not part of your
include path, how about you add it to your CPLUS_INCLUDE_PATH and
C_INCLUDE_PATH env variable in you
This is an automated email from the ASF dual-hosted git repository.
lmzheng pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 39cd612 [Relay][Training] Add more missing gradients (#6767)
add 8e6481e [FIX][AUTOTVM] Make autotvm wor
merrymercy commented on pull request #6790:
URL: https://github.com/apache/incubator-tvm/pull/6790#issuecomment-718297073
@tkonolige Thanks! It is merged.
This is an automated message from the Apache Git Service.
To respond
merrymercy merged pull request #6790:
URL: https://github.com/apache/incubator-tvm/pull/6790
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
masahi commented on pull request #6730:
URL: https://github.com/apache/incubator-tvm/pull/6730#issuecomment-718305745
@jwfromm something is wrong with CI
This is an automated message from the Apache Git Service.
To respond
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 8e6481e [FIX][AUTOTVM] Make autotvm work with spawn (#6790)
add 0c7aae3 [Torch, QNN] Support dynamic quan
masahi merged pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782
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 g
masahi commented on pull request #6782:
URL: https://github.com/apache/incubator-tvm/pull/6782#issuecomment-718358510
Thanks @anijain2305
This is an automated message from the Apache Git Service.
To respond to the message, p
areusch commented on pull request #6703:
URL: https://github.com/apache/incubator-tvm/pull/6703#issuecomment-718367233
@leandron @u99127 @manupa-arm moved the Zephyr portions to #6789 . will
update this one after that merges
FrozenGene commented on a change in pull request #6710:
URL: https://github.com/apache/incubator-tvm/pull/6710#discussion_r514002681
##
File path: python/tvm/auto_scheduler/utils.py
##
@@ -30,7 +30,7 @@
try:
import psutil
except ImportError:
-raise ImportError("psuti
FrozenGene commented on a change in pull request #6710:
URL: https://github.com/apache/incubator-tvm/pull/6710#discussion_r514004465
##
File path: python/tvm/auto_scheduler/utils.py
##
@@ -157,6 +157,9 @@ def __reduce__(self):
def kill_child_processes(parent_pid, sig=signal.
91 matches
Mail list logo