cyx-6 commented on PR #12755:
URL: https://github.com/apache/tvm/pull/12755#issuecomment-1246243022
> Any updates?
All have been updated.
--
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
cyx-6 commented on code in PR #12755:
URL: https://github.com/apache/tvm/pull/12755#discussion_r970315645
##
tests/python/unittest/test_tvmscript_ir_builder_tir.py:
##
@@ -28,18 +28,40 @@
def test_ir_builder_tir_primfunc():
with IRBuilder() as ib:
with
cyx-6 commented on code in PR #12755:
URL: https://github.com/apache/tvm/pull/12755#discussion_r970315472
##
python/tvm/script/ir_builder/tir/ir.py:
##
@@ -65,11 +358,121 @@ def evaluate(value: PrimExpr) -> None:
return _ffi_api.Evaluate(value) # pylint: disable=no-member
cyx-6 commented on code in PR #12755:
URL: https://github.com/apache/tvm/pull/12755#discussion_r970314760
##
python/tvm/script/ir_builder/tir/ir.py:
##
@@ -65,11 +358,121 @@ def evaluate(value: PrimExpr) -> None:
return _ffi_api.Evaluate(value) # pylint: disable=no-member
junrushao commented on PR #12755:
URL: https://github.com/apache/tvm/pull/12755#issuecomment-1246227957
Any updates?
--
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
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from ab8fe34c8e [FQ2I] Quantized constant bias (#12666)
add 91bd9a3fec [Hybrid] Fix handling AST subcription for
junrushao merged PR #12769:
URL: https://github.com/apache/tvm/pull/12769
--
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:
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 64635b7f37 [COMMUNITY] Josh Fromm -> PMC (#12768)
add ab8fe34c8e [FQ2I] Quantized constant bias
Hzfengsy commented on code in PR #12766:
URL: https://github.com/apache/tvm/pull/12766#discussion_r970292569
##
tests/python/unittest/test_tir_schedule_cache_read_write.py:
##
@@ -414,15 +432,15 @@ def cache_read_multi_consumer_target() -> None:
with T.block("A"):
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch torchbench
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit bacf3946c727682e7aad82f03e34abbbd9f120a2
Author: Masahiro Masuda
AuthorDate: Wed Sep 14 13:09:45 2022 +0900
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch torchbench
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 292f55b59b7e82381cb339bfb6f0885b866f097d
Author: YJ Shi
AuthorDate: Wed Jul 6 00:52:34 2022 -0700
add copy_ and
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch torchbench
in repository https://gitbox.apache.org/repos/asf/tvm.git
at bacf3946c7 support constant folding on ndarray_size
This branch includes the following new commits:
new
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch torchbench
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 5aa6d7c25360ee5b339c42f8c9f5c655943a4333
Author: YJ Shi
AuthorDate: Tue Sep 13 16:15:09 2022 -0700
fix rebase
---
linyv commented on issue #12746:
URL: https://github.com/apache/tvm/issues/12746#issuecomment-1246187468
@kparzysz-quic
--
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
linyv commented on issue #12746:
URL: https://github.com/apache/tvm/issues/12746#issuecomment-1246186615
And when building the hexagon_api, the problem is:
-- Looking for Hexagon toolchain in
/local/mnt/workspace/Qualcomm/Hexagon_SDK/4.5.0.3
junrushao commented on code in PR #11639:
URL: https://github.com/apache/tvm/pull/11639#discussion_r970271772
##
src/meta_schedule/schedule_rule/cross_thread_reduction.cc:
##
@@ -184,6 +184,13 @@ class CrossThreadReductionNode : public ScheduleRuleNode {
*/
std::tuple
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 8058423f09 [Hexagon] Create tests to showcase vtcm loading
capabilities on Hexagon. (#12667)
add
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from ef784d68e0 [MetaSchedule][Test] Migrate `check_trace` to
`check_sketch` (#12764)
add 8058423f09
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 64635b7f37 [COMMUNITY] Josh Fromm -> PMC (#12768)
add ab8fe34c8e [FQ2I] Quantized constant bias (#12666)
No
AndrewZhaoLuo merged PR #12666:
URL: https://github.com/apache/tvm/pull/12666
--
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:
vinx13 opened a new pull request, #12769:
URL: https://github.com/apache/tvm/pull/12769
fixed https://github.com/apache/tvm/issues/9955, this is covered by the
existing test case `tests/python/relay/test_op_level3.py::test_unique`
cc @masahi
--
This is an automated message from
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly-docker-update
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 73af5da6e8 [ci][docker] Nightly Docker image update
add ef784d68e0 [MetaSchedule][Test] Migrate
vinx13 commented on code in PR #12749:
URL: https://github.com/apache/tvm/pull/12749#discussion_r970167340
##
src/arith/rewrite_simplify.cc:
##
@@ -1667,6 +1667,22 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
CallNode* op) {
return match.value();
}
}
+
shingjan commented on code in PR #12749:
URL: https://github.com/apache/tvm/pull/12749#discussion_r970115341
##
src/arith/rewrite_simplify.cc:
##
@@ -1667,6 +1667,22 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
CallNode* op) {
return match.value();
}
}
jwfromm commented on PR #12768:
URL: https://github.com/apache/tvm/pull/12768#issuecomment-1245987772
Thank you guys! It's an honor to work with this great community.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
This is an automated email from the ASF dual-hosted git repository.
junrushao pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from 8058423f09 [Hexagon] Create tests to showcase vtcm loading
capabilities on Hexagon. (#12667)
add 64635b7f37
junrushao merged PR #12768:
URL: https://github.com/apache/tvm/pull/12768
--
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:
junrushao commented on PR #12768:
URL: https://github.com/apache/tvm/pull/12768#issuecomment-1245982874
Congrats!!
--
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
shingjan commented on PR #12768:
URL: https://github.com/apache/tvm/pull/12768#issuecomment-1245973629
congrats @jwfromm !
--
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.
tmoreau89 commented on PR #12667:
URL: https://github.com/apache/tvm/pull/12667#issuecomment-1245968374
Thank you @csullivan and @nverke for the PR; it's been merged!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
from ef784d68e0 [MetaSchedule][Test] Migrate `check_trace` to
`check_sketch` (#12764)
add 8058423f09 [Hexagon] Create
tmoreau89 merged PR #12667:
URL: https://github.com/apache/tvm/pull/12667
--
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:
masahi commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970073101
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
masahi commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970068321
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
masahi commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970068321
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
masahi commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970068321
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
masahi commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970067438
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
Lunderberg commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970059913
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
vinx13 commented on code in PR #12720:
URL: https://github.com/apache/tvm/pull/12720#discussion_r970041968
##
python/tvm/tir/tensor_intrin/cuda.py:
##
@@ -36,7 +36,7 @@ def shared_16x32_to_ldmatrix_32x16_layout(i, j):
def shared_32x16_to_ldmatrix_32x16_layout(i, j):
-
mkatanbaf commented on PR #12495:
URL: https://github.com/apache/tvm/pull/12495#issuecomment-1245873861
@tvm-bot rerun
--
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
ZihengJiang opened a new pull request, #12768:
URL: https://github.com/apache/tvm/pull/12768
Dear community:
Please join us to welcome Josh Fromm (@jwfromm) as a new PMC member.
Josh has been continuously working on operator support and robustness across
the whole TVM stack
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a change to branch ziheng/community
in repository https://gitbox.apache.org/repos/asf/tvm.git
omit 5a8a198807 [COMMUNITY] An Wang -> Reviewer
add 1985c0153b [Relay][Layout] Add FInferCorrectLayout for L2
This is an automated email from the ASF dual-hosted git repository.
ziheng pushed a commit to branch ziheng/community
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit a04a19537cfcf2b30d4afdc85ae36a572848552c
Author: ZihengJiang
AuthorDate: Tue Sep 13 12:07:31 2022 -0700
vinx13 closed issue #12767: [Bug] How to register op by c++.
URL: https://github.com/apache/tvm/issues/12767
--
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,
vinx13 commented on issue #12767:
URL: https://github.com/apache/tvm/issues/12767#issuecomment-1245812224
You can register typed packed func using `set_body_typed` so that you don't
have to accept `TVMArgs`
--
This is an automated message from the Apache Git Service.
To respond to the
zxybazh commented on issue #12298:
URL: https://github.com/apache/tvm/issues/12298#issuecomment-1245780922
> cc @zxybazh Hi~ could you reproduce the
https://gist.github.com/zxybazh/0759810aa841508c68abbdf7a00c4ab2 on current
HEAD? I failed to reproduce the split verification error...,
tqchen commented on issue #12743:
URL: https://github.com/apache/tvm/issues/12743#issuecomment-1245734689
+1
TQ
--
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
Icemist commented on code in PR #12545:
URL: https://github.com/apache/tvm/pull/12545#discussion_r969902913
##
python/tvm/autotvm/task/space.py:
##
@@ -822,11 +826,262 @@ def valid(self):
"""
return not bool(self.errors)
+def is_index_valid(self, index):
zxybazh commented on issue #12743:
URL: https://github.com/apache/tvm/issues/12743#issuecomment-1245721784
+1
--
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
janetsc commented on code in PR #12727:
URL: https://github.com/apache/tvm/pull/12727#discussion_r969898294
##
src/runtime/hexagon/hexagon_device_api.h:
##
@@ -45,11 +45,27 @@ class HexagonDeviceAPI final : public DeviceAPI {
static HexagonDeviceAPI* Global();
//!
nverke commented on PR #12654:
URL: https://github.com/apache/tvm/pull/12654#issuecomment-1245697544
@adstraw I believe I made the code more clear as to which are producers but
let me know what you think!
--
This is an automated message from the Apache Git Service.
To respond to the
nverke commented on code in PR #12654:
URL: https://github.com/apache/tvm/pull/12654#discussion_r969881212
##
tests/python/contrib/test_hexagon/test_parallel_scalar.py:
##
@@ -0,0 +1,178 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
ekalda commented on PR #12456:
URL: https://github.com/apache/tvm/pull/12456#issuecomment-1245625785
@driazati @areusch @leandron it's passing the CI now after the upgrade to
the Docker image, so should be fine to merge.
--
This is an automated message from the Apache Git Service.
To
gromero commented on PR #12762:
URL: https://github.com/apache/tvm/pull/12762#issuecomment-1245612645
> Hi @srkreddy1238, thanks for the PR. Can you improve the commit message
with the actual operators are being added?
@srkreddy1238 You can look at
Lunderberg commented on PR #10516:
URL: https://github.com/apache/tvm/pull/10516#issuecomment-1245607258
I let this one languish long enough that I no longer trust the CI checks to
be up-to-date. Re-running CI.
--
This is an automated message from the Apache Git Service.
To respond to
gromero commented on PR #12756:
URL: https://github.com/apache/tvm/pull/12756#issuecomment-1245575351
> One comment depending on your usage, otherwise LGTM
@erwango Thanks for the review! I've got some additional question about the
`Q` and `P` params and associated clocks before we
gromero commented on code in PR #12756:
URL: https://github.com/apache/tvm/pull/12756#discussion_r969771963
##
apps/microtvm/zephyr/template_project/app-overlay/nucleo_l4r5zi.overlay:
##
@@ -21,3 +21,29 @@
{
clock-frequency = ;
};
+
+/* Set PLL, where:
+
+ VCO freq
Lunderberg commented on PR #12720:
URL: https://github.com/apache/tvm/pull/12720#issuecomment-1245512099
Looks like the final failing unit test is due to an incorrect mapping in
`tir.tensor_intrin.cuda.shared_32x16_to_ldmatrix_32x16_layout`. It currently
returns `[(i % 4) + 4 * (j % 8), 8
ekalda commented on code in PR #93:
URL: https://github.com/apache/tvm-rfcs/pull/93#discussion_r969575317
##
rfcs/0093_Issue_Triage.md:
##
@@ -0,0 +1,309 @@
+# Issue Triage
+
+* Feature Name: `Update Issue Triage Workflow`
+* Co-authored with @areusch, @denise
+
+# **Summary**
This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch last-successful
in repository https://gitbox.apache.org/repos/asf/tvm.git
from a23b71ce1e [MetaSchedule][Test] Migrate AddRFactor to SEqual (#12758)
add ef784d68e0
loveppdog opened a new issue, #12767:
URL: https://github.com/apache/tvm/issues/12767
I want to register support op by c++ to implement the following func like
python code.
@tvm.ir.register_op_attr("nn.avg_pool2d","dnnl")
def avg_pool2d_check(expr):
attrs, args = expr.attrs,
Yangzijun510 closed pull request #12765: [Bugfix] letnode too much make dump
ir samll
URL: https://github.com/apache/tvm/pull/12765
--
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
Yangzijun510 opened a new pull request, #12765:
URL: https://github.com/apache/tvm/pull/12765
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
sfvaroglu commented on PR #12729:
URL: https://github.com/apache/tvm/pull/12729#issuecomment-1245217914
@tvm-bot rerun
--
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
MichaelJKlaiber commented on PR #12731:
URL: https://github.com/apache/tvm/pull/12731#issuecomment-1245170081
@areusch, @manupak , what are your 2cents here?
This seems like a minor fix.
--
This is an automated message from the Apache Git Service.
To respond to the message, please
This is an automated email from the ASF dual-hosted git repository.
syfeng 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 ef784d68e0 [MetaSchedule][Test] Migrate `check_trace`
Hzfengsy merged PR #12764:
URL: https://github.com/apache/tvm/pull/12764
--
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:
erwango commented on code in PR #12756:
URL: https://github.com/apache/tvm/pull/12756#discussion_r969342711
##
apps/microtvm/zephyr/template_project/app-overlay/nucleo_l4r5zi.overlay:
##
@@ -21,3 +21,29 @@
{
clock-frequency = ;
};
+
+/* Set PLL, where:
+
+ VCO freq
masahi commented on code in PR #12318:
URL: https://github.com/apache/tvm/pull/12318#discussion_r969284123
##
gallery/how_to/work_with_pytorch/using_optimized_torch.py:
##
@@ -0,0 +1,176 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
masahi commented on code in PR #12318:
URL: https://github.com/apache/tvm/pull/12318#discussion_r969252514
##
gallery/how_to/work_with_pytorch/using_as_torch.py:
##
@@ -0,0 +1,171 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor license
junrushao opened a new pull request, #12764:
URL: https://github.com/apache/tvm/pull/12764
This PR further migrates more `check_trace` (string equality of traces) to
`check_sketch` (structural equality of TIR) for the following schedule rules:
- AutoBind
- RandomComputeLocation
-
mkatanbaf commented on PR #12495:
URL: https://github.com/apache/tvm/pull/12495#issuecomment-1244986090
@tvm-bot rerun
--
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
billishyahao opened a new issue, #12763:
URL: https://github.com/apache/tvm/issues/12763
When we invoke
```
relay_mod = relay.transform.ToMixedPrecision('bfloat16')(relay_mod)
```
pass, we are supposed to get a well-transformed model which contains
different kinds of operators
elvin-n commented on code in PR #12545:
URL: https://github.com/apache/tvm/pull/12545#discussion_r969214283
##
python/tvm/autotvm/task/space.py:
##
@@ -822,11 +826,262 @@ def valid(self):
"""
return not bool(self.errors)
+def is_index_valid(self, index):
srkreddy1238 opened a new pull request, #12762:
URL: https://github.com/apache/tvm/pull/12762
* Enabled Resnet & InceptionV3
* FP16 support added for CLML ops.
Co-authored-by: Krishna Raju
Co-authored-by: Shwetank Singh
Thanks for contributing to TVM! Please
75 matches
Mail list logo