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 e8de2c5 [AutoSchedule] Extract tasks via compile engine (#6903)
add 6c01998 Make AutoScheduler handling
monklof commented on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-728764439
> 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.
Hi, this is the ca
merrymercy merged pull request #6909:
URL: https://github.com/apache/incubator-tvm/pull/6909
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
merrymercy commented on pull request #6909:
URL: https://github.com/apache/incubator-tvm/pull/6909#issuecomment-728764382
Thanks, @TaylorZowtuk. It is merged.
This is an automated message from the Apache Git Service.
To respo
monklof edited a comment on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-728764439
> 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.
Hi, this is
monklof edited a comment on pull request #6898:
URL: https://github.com/apache/incubator-tvm/pull/6898#issuecomment-728764439
@wweic @lixiaoquan thanks for the comment.
@icemelon9
> I have a question. What do you mean "input's shape's second dim is
unknown"? TVM is able to compil
fanwei-china opened a new issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931
Thanks for participating in the TVM community! We use https://discuss.tvm.ai
for any general usage questions and discussions. The issue tracker is used for
actionable items such as feature propo
fanwei-china commented on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728774631
Traceback (most recent call last):
File "tutorials/frontend/test_nlp.py", line 109, in
shape=shape_dict)
File
"/root/.local/lib/python3.6/site-
fanwei-china removed a comment on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728774631
Traceback (most recent call last):
File "tutorials/frontend/test_nlp.py", line 109, in
shape=shape_dict)
File
"/root/.local/lib/python3
fanwei-china commented on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728783274
the IRModule is below:
fn (%bert/embeddings/word_embedding: Tensor[(249079, 384), float32],
%qt_sent: Tensor[(512, 50), int32], %n_keyword_in: Tensor[(512, 10), int32]
fanwei-china commented on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728785484
the tensorflow frontend code is:
with tf_compat_v1.gfile.GFile(model_path, 'rb') as f:
graph_def = tf_compat_v1.GraphDef()
graph_def.ParseFromString(f.r
fanwei-china edited a comment on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728785484
the tensorflow frontend code is:
with tf_compat_v1.gfile.GFile(model_path, 'rb') as f:
graph_def = tf_compat_v1.GraphDef()
graph_def.ParseFromStr
fanwei-china commented on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728787606
> ```
> Hi, I was trying to import bert model by tensorflow relay. When
converting the StrideSlice op, an error occurred. Could someone help me to
solve this? The cod
fanwei-china removed a comment on issue #6931:
URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728787606
> ```
> Hi, I was trying to import bert model by tensorflow relay. When
converting the StrideSlice op, an error occurred. Could someone help me to
solve this?
bernhardklein commented on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728834693
@merrymercy as you suggested I set the constructor argument to `(timeout *
(self.n_parallel + 1))`, also changed the self.timeout in the same way. Hope
this is the c
merrymercy commented on a change in pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#discussion_r525061557
##
File path: python/tvm/autotvm/measure/measure_methods.py
##
@@ -228,7 +228,7 @@ def __init__(
self.host = host
self.port = p
merrymercy commented on a change in pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#discussion_r525061819
##
File path: python/tvm/autotvm/measure/measure_methods.py
##
@@ -240,7 +240,7 @@ def __init__(
self.check_correctness = check_correctn
merrymercy commented on a change in pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#discussion_r525062032
##
File path: python/tvm/autotvm/measure/measure_methods.py
##
@@ -240,7 +240,7 @@ def __init__(
self.check_correctness = check_correctn
merrymercy edited a comment on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728850614
You should only change the timeout setting in `LocalExecutor`.
The `self.timeout` is used in other places and it is correct.
I helped you to fix the problems
merrymercy commented on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728850614
You should only change the timeout setting in `LocalExecutor`.
The `self.timeout` is used in other places and it is correct.
merrymercy edited a comment on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728850614
You should only change the timeout setting in `LocalExecutor`.
The `self.timeout` is used in other places and it is correct.
I helped you fix the problems.
merrymercy commented on a change in pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#discussion_r525064535
##
File path: python/tvm/autotvm/measure/measure_methods.py
##
@@ -240,7 +240,7 @@ def __init__(
self.check_correctness = check_correctn
BhushanIMG commented on pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477#issuecomment-728853701
@FrozenGene Could you please spare some time to review this.
This is an automated message from the Apac
bernhardklein commented on pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924#issuecomment-728878293
ok, thank you!
This is an automated message from the Apache Git Service.
To respond to the message,
tirumalnaidu commented on pull request #5630:
URL: https://github.com/apache/incubator-tvm/pull/5630#issuecomment-728891764
``Traceback (most recent call last):
File "/usr/lib/python3.6/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
File "/usr/lib/python3.6
tirumalnaidu edited a comment on pull request #5630:
URL: https://github.com/apache/incubator-tvm/pull/5630#issuecomment-728891764
Traceback (most recent call last):
File "/usr/lib/python3.6/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
File "/usr/lib/pyth
FrozenGene merged pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477
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
FrozenGene commented on pull request #6477:
URL: https://github.com/apache/incubator-tvm/pull/6477#issuecomment-728913714
thanks @BhushanIMG
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.
zhaowu pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 6c01998 Make AutoScheduler handling of errors during measure
consistent with AutoTvm (#6909)
add 7e90e7d
tirumalnaidu opened a new issue #6932:
URL: https://github.com/apache/incubator-tvm/issues/6932
Traceback (most recent call last):
File "/usr/lib/python3.6/multiprocessing/process.py", line 258, in
_bootstrap
self.run()
File "/usr/lib/python3.6/multiprocessing/process.py",
giuseros commented on a change in pull request #6928:
URL: https://github.com/apache/incubator-tvm/pull/6928#discussion_r525237522
##
File path: python/tvm/topi/tensor.py
##
@@ -73,3 +75,341 @@ def full_like(x, fill_value):
The result.
"""
return cpp.full_lik
mbaret commented on a change in pull request #6907:
URL: https://github.com/apache/incubator-tvm/pull/6907#discussion_r525292288
##
File path: python/tvm/topi/arm_cpu/tensor_intrin.py
##
@@ -447,28 +88,280 @@ def gemm_quantized(M, N, K, unroll, interleave, in_type,
out_type):
mbaret commented on pull request #6907:
URL: https://github.com/apache/incubator-tvm/pull/6907#issuecomment-729052539
cc @FrozenGene @yzhliu if you're interested
This is an automated message from the Apache Git Service.
To re
merrymercy closed issue #6922:
URL: https://github.com/apache/incubator-tvm/issues/6922
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
merrymercy merged pull request #6924:
URL: https://github.com/apache/incubator-tvm/pull/6924
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
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 7e90e7d [Relay] Add space_to_batch_nd and batch_to_space_nd operators
(#6477)
add 47809c3 [AutoTVM][RPC
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 7e90e7d [Relay] Add space_to_batch_nd and batch_to_space_nd operators
(#6477)
add 47809c3 [AutoTVM][RPC
comaniac commented on pull request #6855:
URL: https://github.com/apache/incubator-tvm/pull/6855#issuecomment-729067658
@euntaik please address the review comments.
This is an automated message from the Apache Git Service.
To
tqchen merged pull request #6886:
URL: https://github.com/apache/incubator-tvm/pull/6886
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 47809c3 [AutoTVM][RPCRunner] timeout is not passed correctly (#6924)
add b236f10 [CI] Install libc6-dev-i
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 47809c3 [AutoTVM][RPCRunner] timeout is not passed correctly (#6924)
add b236f10 [CI] Install libc6-dev-i
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 47809c3 [AutoTVM][RPCRunner] timeout is not passed correctly (#6924)
add b236f10 [CI] Install libc6-dev-i
areusch commented on pull request #6930:
URL: https://github.com/apache/incubator-tvm/pull/6930#issuecomment-729120351
@tqchen @tom-gall @u99127 @manupa-arm
Note: this mostly impacts the x86 flow used with test_crt, but submitting
this to make things not broken and more maintainable
mbrookhart commented on a change in pull request #6839:
URL: https://github.com/apache/incubator-tvm/pull/6839#discussion_r525432512
##
File path: python/tvm/topi/cuda/nms.py
##
@@ -519,14 +557,90 @@ def non_max_suppression(
coord_start,
id_index,
trevor-m opened a new pull request #6933:
URL: https://github.com/apache/incubator-tvm/pull/6933
* Support NonMaxSuppressionV5 aka
`tf.image.non_max_suppression_with_scores` which returns scores in addition to
indices and size
(https://github.com/tensorflow/tensorflow/commit/eb10dcf81a30
tqchen commented on a change in pull request #6910:
URL: https://github.com/apache/incubator-tvm/pull/6910#discussion_r525552389
##
File path: tests/python/unittest/test_node_reflection.py
##
@@ -57,7 +57,7 @@ def test_make_smap():
def test_make_node():
-x = tvm.ir.mak
jroesch commented on a change in pull request #6839:
URL: https://github.com/apache/incubator-tvm/pull/6839#discussion_r525566209
##
File path: tests/python/frontend/onnx/test_forward.py
##
@@ -3889,78 +3986,7 @@ def test_if():
if __name__ == "__main__":
-test_flatten(
tkonolige commented on a change in pull request #6910:
URL: https://github.com/apache/incubator-tvm/pull/6910#discussion_r525572549
##
File path: tests/python/unittest/test_node_reflection.py
##
@@ -57,7 +57,7 @@ def test_make_smap():
def test_make_node():
-x = tvm.ir.
jroesch commented on pull request #6886:
URL: https://github.com/apache/incubator-tvm/pull/6886#issuecomment-729257691
Looks good to me, was on vacation for a few days, thanks for the fix!
This is an automated message from th
tqchen commented on pull request #6886:
URL: https://github.com/apache/incubator-tvm/pull/6886#issuecomment-729262365
@jroesch still need to update the images to reflect the change
This is an automated message from the Apache
tqchen commented on a change in pull request #6910:
URL: https://github.com/apache/incubator-tvm/pull/6910#discussion_r525579597
##
File path: tests/python/unittest/test_node_reflection.py
##
@@ -57,7 +57,7 @@ def test_make_smap():
def test_make_node():
-x = tvm.ir.mak
jroesch commented on a change in pull request #6874:
URL: https://github.com/apache/incubator-tvm/pull/6874#discussion_r525586496
##
File path: src/parser/parser.cc
##
@@ -605,30 +605,42 @@ class Parser {
return ast;
}
+ struct MetaRef {
Review comment:
Yes t
zhiics merged pull request #6933:
URL: https://github.com/apache/incubator-tvm/pull/6933
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
zhiics commented on pull request #6933:
URL: https://github.com/apache/incubator-tvm/pull/6933#issuecomment-729281956
Thanks @trevor-m @kevinthesun
This is an automated message from the Apache Git Service.
To respond to the
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 b236f10 [CI] Install libc6-dev-i386 to compile wasm32 (#6886)
add 0f5b5fe [TensorFlow] Support NonMaxSuppre
comaniac opened a new pull request #6934:
URL: https://github.com/apache/incubator-tvm/pull/6934
After loading the log file to restore the task scheduler state:
* In the round-robin stage, skip the tasks which `ct` is greater than zero,
meaning that they have been tuned before.
* Rest
jroesch commented on pull request #6886:
URL: https://github.com/apache/incubator-tvm/pull/6886#issuecomment-729304036
@tqchen these tests are only ran on CPU so I should only have to update that
image right?
This is an auto
jroesch merged pull request #6920:
URL: https://github.com/apache/incubator-tvm/pull/6920
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.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 0f5b5fe [TensorFlow] Support NonMaxSuppressionV5 (#6933)
add 51d81fb [DOC] Fix typo (#6920)
No new revi
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 0f5b5fe [TensorFlow] Support NonMaxSuppressionV5 (#6933)
add 51d81fb [DOC] Fix typo (#6920)
No new revi
tqchen commented on pull request #6886:
URL: https://github.com/apache/incubator-tvm/pull/6886#issuecomment-729310802
Right
This is an automated message from the Apache Git Service.
To respond to the message, please log on t
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 0f5b5fe [TensorFlow] Support NonMaxSuppressionV5 (#6933)
add 51d81fb [DOC] Fix typo (#6920)
No new revi
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 0f5b5fe [TensorFlow] Support NonMaxSuppressionV5 (#6933)
add 51d81fb [DOC] Fix typo (#6920)
No new revi
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 0f5b5fe [TensorFlow] Support NonMaxSuppressionV5 (#6933)
add 51d81fb [DOC] Fix typo (#6920)
No new revi
areusch commented on pull request #6917:
URL: https://github.com/apache/incubator-tvm/pull/6917#issuecomment-729341714
@tqchen @u99127 @tom-gall @manupa-arm @leandron
This is an automated message from the Apache Git Service.
merrymercy opened a new pull request #6935:
URL: https://github.com/apache/incubator-tvm/pull/6935
Improve the warning messages for #6903
This is an automated message from the Apache Git Service.
To respond to the message, p
merrymercy commented on a change in pull request #6935:
URL: https://github.com/apache/incubator-tvm/pull/6935#discussion_r525703085
##
File path: python/tvm/relay/op/strategy/cuda.py
##
@@ -224,7 +231,7 @@ def conv2d_strategy_cuda(attrs, inputs, out_type, target):
merrymercy commented on a change in pull request #6935:
URL: https://github.com/apache/incubator-tvm/pull/6935#discussion_r525703690
##
File path: python/tvm/relay/op/strategy/cuda.py
##
@@ -224,7 +231,7 @@ def conv2d_strategy_cuda(attrs, inputs, out_type, target):
merrymercy commented on a change in pull request #6927:
URL: https://github.com/apache/incubator-tvm/pull/6927#discussion_r525709883
##
File path: python/tvm/auto_scheduler/search_task.py
##
@@ -63,6 +66,11 @@ def __getstate__(self):
def __setstate__(self, state):
merrymercy commented on a change in pull request #6927:
URL: https://github.com/apache/incubator-tvm/pull/6927#discussion_r525709883
##
File path: python/tvm/auto_scheduler/search_task.py
##
@@ -63,6 +66,11 @@ def __getstate__(self):
def __setstate__(self, state):
yzhliu opened a new pull request #6936:
URL: https://github.com/apache/incubator-tvm/pull/6936
Please join us to welcome @mbrookhart as a new committer.
Matthew is one of the major authors of pattern language in Relay, which has
been one of the essential infrastructure tools and has
solin319 edited a comment on pull request #6904:
URL: https://github.com/apache/incubator-tvm/pull/6904#issuecomment-726550528
Already add cudnn test in test_topi_conv3d_ncdhw.py
@tqchen
This is an automated message from
comaniac commented on a change in pull request #6935:
URL: https://github.com/apache/incubator-tvm/pull/6935#discussion_r525860346
##
File path: python/tvm/relay/op/strategy/cuda.py
##
@@ -101,6 +101,17 @@ def schedule_lrn_cuda(attrs, outs, target):
return topi.cuda.sc
comaniac merged pull request #6934:
URL: https://github.com/apache/incubator-tvm/pull/6934
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.
comaniac pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 51d81fb [DOC] Fix typo (#6920)
add cc727f7 [AutoScheduler] Fix task scheduler restoring (#6934)
No new
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 51d81fb [DOC] Fix typo (#6920)
add cc727f7 [AutoScheduler] Fix task scheduler restoring (#6934)
No new
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 51d81fb [DOC] Fix typo (#6920)
add cc727f7 [AutoScheduler] Fix task scheduler restoring (#6934)
No new
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 51d81fb [DOC] Fix typo (#6920)
add cc727f7 [AutoScheduler] Fix task scheduler restoring (#6934)
No new
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 51d81fb [DOC] Fix typo (#6920)
add cc727f7 [AutoScheduler] Fix task scheduler restoring (#6934)
No new
79 matches
Mail list logo