This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 32e500b7f7 [LLVM] Add support to generate llvm.assume (#14294)
add d1dea13762 [Bugfix][TVMScript] Preserve vari
This is an automated email from the ASF dual-hosted git repository.
ruihangl pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 2ff41c6156 [TIR][Schedule] Allow buffer name argument
MasterJH5574 merged PR #14327:
URL: https://github.com/apache/tvm/pull/14327
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apa
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140897734
##
tests/python/relax/test_transform_convert_layout.py:
##
@@ -0,0 +1,1211 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140849081
##
include/tvm/relax/transform.h:
##
@@ -279,6 +279,14 @@ TVM_DLL Pass RunCodegen(Optional>> target_opt
* \return The Pass.
*/
TVM_DLL Pass SimplifyNormInfer
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch unity
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/unity by this push:
new 5513095b5a [Unity][BYOC] Improve expressiveness of th
masahi merged PR #14310:
URL: https://github.com/apache/tvm/pull/14310
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
zxybazh opened a new issue, #14328:
URL: https://github.com/apache/tvm/issues/14328
In the following script where we try to print out the IRModule, the printed
out script will have `T_equal[v_ax0, v_ax1] = rxplaceholder[v_ax0, v_ax1] ==
True` which cannot be parsed back to IRModule.
yelite commented on code in PR #14310:
URL: https://github.com/apache/tvm/pull/14310#discussion_r1140717005
##
include/tvm/relax/transform.h:
##
@@ -215,17 +215,108 @@ TVM_DLL Pass AnnotateTIROpPattern();
*/
TVM_DLL Pass FuseOps(int fuse_opt_level = -1);
+/*!
+ * \brief The
tvm-bot commented on PR #14327:
URL: https://github.com/apache/tvm/pull/14327#issuecomment-1474281842
Thanks for contributing to TVM! Please refer to the contributing guidelines
https://tvm.apache.org/docs/contribute/ for useful information and tips. Please
request code reviews from
Lunderberg opened a new pull request, #14327:
URL: https://github.com/apache/tvm/pull/14327
Similar to other schedule primitives, allow the buffer argument to
`Schedule.set_scope` to be passed as a human-readable name instead of a numeric
index. This change is solely in the Python API, and
zxybazh commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140580956
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
yongwww commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140575778
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
yongwww commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140573049
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140560973
##
src/relax/transform/convert_layout.cc:
##
@@ -0,0 +1,323 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor license
zxybazh commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140553703
##
src/relax/op/tensor/index.cc:
##
@@ -24,6 +24,7 @@
#include "index.h"
+#include
Review Comment:
Thanks for pointing this out. It's a fix for linting because
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140528647
##
tests/python/relax/test_transform_convert_layout.py:
##
@@ -0,0 +1,1211 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140528102
##
tests/python/relax/test_transform_convert_layout.py:
##
@@ -0,0 +1,1211 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
This is an automated email from the ASF dual-hosted git repository.
mehrdadh pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new ca8153d502 [AOT]Raise error when input name is not va
mehrdadh closed issue #13013: [Runtime][AOTExecutor] set_input does not show
error if input name does not exist in the model
URL: https://github.com/apache/tvm/issues/13013
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
mehrdadh merged PR #14322:
URL: https://github.com/apache/tvm/pull/14322
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.
This is an automated email from the ASF dual-hosted git repository.
mehrdadh pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 4ae08d8710 [apps][bundle_deploy]Fix bundle build issu
mehrdadh closed issue #13996: [CI Problem] apps/bundle_deploy test cases are
not tested independently in the CI
URL: https://github.com/apache/tvm/issues/13996
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL abov
mehrdadh merged PR #14315:
URL: https://github.com/apache/tvm/pull/14315
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.
sunggg commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140504591
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
re
spectrometerHBH commented on code in PR #14257:
URL: https://github.com/apache/tvm/pull/14257#discussion_r1140505411
##
tests/python/relax/test_transform_convert_layout.py:
##
@@ -0,0 +1,1211 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
sunggg commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140504591
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
re
slyubomirsky commented on code in PR #14282:
URL: https://github.com/apache/tvm/pull/14282#discussion_r1140500288
##
src/relax/op/op.cc:
##
@@ -315,6 +315,32 @@ Expr MakeShapeOf(Expr expr) {
TVM_REGISTER_GLOBAL("relax.op.shape_of").set_body_typed(MakeShapeOf);
+// tensor_to
This is an automated email from the ASF dual-hosted git repository.
driazati pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 84e8f86960 [docs] Add details about patch releases (#
driazati merged PR #14301:
URL: https://github.com/apache/tvm/pull/14301
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.
yongwww commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140457693
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
sunggg commented on code in PR #14282:
URL: https://github.com/apache/tvm/pull/14282#discussion_r1140477714
##
src/relax/op/op.cc:
##
@@ -315,6 +315,32 @@ Expr MakeShapeOf(Expr expr) {
TVM_REGISTER_GLOBAL("relax.op.shape_of").set_body_typed(MakeShapeOf);
+// tensor_to_shape
slyubomirsky commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140470028
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
slyubomirsky commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140470028
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
slyubomirsky commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140470028
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
yongwww commented on PR #14324:
URL: https://github.com/apache/tvm/pull/14324#issuecomment-1474107208
for question 1, I would prefer to keep it static if it is not data-dependent
cases, raising error during runtime when the dim is not valid should be fine to
me.
--
This is an automated m
yongwww commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140457693
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
yongwww commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140457693
##
tests/python/relax/test_op_index.py:
##
@@ -376,22 +409,22 @@ def test_strided_slice_infer_struct_info_shape_symbolic():
_check_inference(
bb,
r
slyubomirsky commented on code in PR #14324:
URL: https://github.com/apache/tvm/pull/14324#discussion_r1140454331
##
src/relax/op/tensor/index.cc:
##
@@ -24,6 +24,7 @@
#include "index.h"
+#include
Review Comment:
What is used from `std::algorithm` here?
--
This is
slyubomirsky commented on PR #14324:
URL: https://github.com/apache/tvm/pull/14324#issuecomment-1474094980
It would be nice to have a single source of truth for shape inference, if
that's what you're referring to in question 2.
What exactly is question 1 referring to? You can use `Mat
slyubomirsky commented on code in PR #14282:
URL: https://github.com/apache/tvm/pull/14282#discussion_r1140442382
##
src/relax/op/op.cc:
##
@@ -315,6 +315,32 @@ Expr MakeShapeOf(Expr expr) {
TVM_REGISTER_GLOBAL("relax.op.shape_of").set_body_typed(MakeShapeOf);
+// tensor_to
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140430525
##
src/runtime/hexagon/hexagon_device_api.cc:
##
@@ -233,6 +233,19 @@
TVM_REGISTER_GLOBAL("device_api.hexagon.dma_wait").set_body([](TVMArgs args, TVM
*rv = static_ca
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140387258
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140366250
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140368645
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140368645
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140368645
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140366250
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw commented on code in PR #14254:
URL: https://github.com/apache/tvm/pull/14254#discussion_r1140365973
##
include/tvm/tir/builtin.h:
##
@@ -726,15 +726,26 @@ TVM_DLL const Op& texture2d_store();
TVM_DLL const Op& texture2d_load();
/*!
- * \brief Initiate a non-blocking
adstraw closed pull request #14258: [Hexagon] Ensure DMA has ownership before
issuing copy
URL: https://github.com/apache/tvm/pull/14258
--
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 the specific
tqchen commented on PR #14316:
URL: https://github.com/apache/tvm/pull/14316#issuecomment-1473977633
how about `unsafe_set_dtype`, with document to users that this operation can
change the model behavior.
--
This is an automated message from the Apache Git Service.
To respond to the messa
Lunderberg commented on PR #14320:
URL: https://github.com/apache/tvm/pull/14320#issuecomment-1473951122
@junrushao Thank you, and I can work around the issue by using an explicit
`T.FloorDiv`, so this isn't by any means a blocking issue for me. It's more
that it was an unexpected change,
Lunderberg commented on PR #14318:
URL: https://github.com/apache/tvm/pull/14318#issuecomment-1473921109
Thank you @cyx-6 , and those are definitely good reasons. I like the
general simplifications, and that especially makes sense to re-use the
auto-value promotion.
> Actually, the
This is an automated email from the ASF dual-hosted git repository.
kparzysz pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new f7c2bbbe87 [LLVM] Fix registerCallbacks API after rec
kparzysz-quic merged PR #14323:
URL: https://github.com/apache/tvm/pull/14323
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.ap
rebel-jangys opened a new issue, #14326:
URL: https://github.com/apache/tvm/issues/14326
https://github.com/apache/tvm/blob/fe3fa9d75d6bda75cca644516b3cbcdedd0354a8/src/relay/op/nn/convolution.cc#L597
https://github.com/apache/tvm/blob/fe3fa9d75d6bda75cca644516b3cbcdedd0354a8/src/rel
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new fe3fa9d75d [Fix][TIR] Fix tvm::arith::UnionLowerBound (
masahi merged PR #14304:
URL: https://github.com/apache/tvm/pull/14304
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
Author: leandron
Date: Fri Mar 17 09:44:26 2023
New Revision: 60685
Log:
Move TVM v0.11.1 to the release after vote results have been published.
Added:
release/tvm/tvm-v0.11.1/
- copied from r60684, dev/tvm/tvm-v0.11.1/
Removed:
dev/tvm/tvm-v0.11.1/
leandron closed issue #14325: [RESULT] [VOTE] Release Apache TVM v0.11.1
URL: https://github.com/apache/tvm/issues/14325
--
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 the specific comment.
To unsu
leandron commented on issue #14260:
URL: https://github.com/apache/tvm/issues/14260#issuecomment-1473528562
Closing this vote as results have been published.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL abov
leandron closed issue #14259: TVM v0.11.1 Release Candidate Notes
URL: https://github.com/apache/tvm/issues/14259
--
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 the specific comment.
To unsubscribe
leandron closed issue #14260: [VOTE] Release Apache TVM v0.11.1
URL: https://github.com/apache/tvm/issues/14260
--
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 the specific comment.
To unsubscribe,
leandron commented on issue #14259:
URL: https://github.com/apache/tvm/issues/14259#issuecomment-1473528117
Closing as release is published.
--
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 the sp
leandron opened a new issue, #14325:
URL: https://github.com/apache/tvm/issues/14325
Dear TVM community,
I'm glad to announce the results of the vote for the release of the
v0.11.0.rc0 package. This vote passes with 7 "+1 votes" (5 binding), no "0
votes", and no "-1 vote".
+1
lileidev commented on issue #13634:
URL: https://github.com/apache/tvm/issues/13634#issuecomment-1473523968
Seems that gm.set_output_zero_copy(0, tvm.nd.from_dlpack(z_data)) affected
output value. If comment this line, gm.get_output(0).numpy() will get correct
value.
--
This is an auto
Biubiubiu12 commented on PR #14304:
URL: https://github.com/apache/tvm/pull/14304#issuecomment-1473464289
> Please make the CI green and we can get it in :-)
Hi, CI is finished.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to
masahi merged PR #14290:
URL: https://github.com/apache/tvm/pull/14290
--
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 the specific comment.
To unsubscribe, e-mail: commits-unsubscr...@tvm.apache.or
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/tvm.git
from 58dce66097 [CI] Update CUDA to 11.7 (#14293)
add 3f2dac0d07 [PaddlePaddle Hackathon 4][Frontend][Paddle]add conv3d for
69 matches
Mail list logo