[GitHub] [incubator-tvm] zhxfl commented on issue #6891: gcc8.2 compile error

zhxfl commented on issue #6891: URL: https://github.com/apache/incubator-tvm/issues/6891#issuecomment-724559719 DataType is not a Derived classof ObjectRef. static_assert(std::is_base_of) fail; gcc53 can compile sussess

[GitHub] [incubator-tvm] lixiaoquan opened a new pull request #6892: [Relay] Add dynamic SparseToDense

lixiaoquan opened a new 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

[GitHub] [incubator-tvm] zhxfl closed issue #6891: gcc8.2 compile error

zhxfl closed issue #6891: URL: https://github.com/apache/incubator-tvm/issues/6891 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

[GitHub] [incubator-tvm] giuseros commented on a change in pull request #6864: Qnn for first conv

giuseros commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r520632201 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] FrozenGene commented on issue #6891: gcc8.2 compile error

FrozenGene commented on issue #6891: URL: https://github.com/apache/incubator-tvm/issues/6891#issuecomment-724662362 https://github.com/apache/incubator-tvm/pull/6893 should solve the this issue @zhxfl This is an automated

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #6887: Fix bug of generate-unmatched-brackets in CodeGenC::PrintSSAAssign

tqchen commented on a change in pull request #6887: URL: https://github.com/apache/incubator-tvm/pull/6887#discussion_r520560320 ## File path: src/target/source/codegen_c.cc ## @@ -139,11 +139,29 @@ void CodeGenC::PrintExpr(const PrimExpr& n, std::ostream& os) { // NOLINT(*)

[GitHub] [incubator-tvm] Light-of-Hers commented on pull request #6887: Fix bug of generate-unmatched-brackets in CodeGenC::PrintSSAAssign

Light-of-Hers commented on pull request #6887: URL: https://github.com/apache/incubator-tvm/pull/6887#issuecomment-724726901 Sorry, some low-level mistakes. Is it okay now? @tqchen This is an automated message from the

[GitHub] [incubator-tvm] FrozenGene opened a new pull request #6893: [GCC] Fix GCC8.1 and GCC8.2 template dispatch compilation issue

FrozenGene opened a new pull request #6893: URL: https://github.com/apache/incubator-tvm/pull/6893 Solve https://github.com/apache/incubator-tvm/issues/6891 I could confirm this is the same issue of https://gcc.gnu.org/bugzilla/show_bug.cgi?id=86246 and

[GitHub] [incubator-tvm] zhxfl commented on issue #6891: gcc8.2 compile error

zhxfl commented on issue #6891: URL: https://github.com/apache/incubator-tvm/issues/6891#issuecomment-724670552 fix now & tks This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [incubator-tvm] tqchen commented on pull request #6887: Fix bug of generate-unmatched-brackets in CodeGenC::PrintSSAAssign

tqchen commented on pull request #6887: URL: https://github.com/apache/incubator-tvm/pull/6887#issuecomment-724959748 Thanks @Light-of-Hers ! This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] tqchen merged pull request #6893: [GCC] Fix GCC8.1 and GCC8.2 template dispatch compilation issue

tqchen merged pull request #6893: URL: https://github.com/apache/incubator-tvm/pull/6893 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

[incubator-tvm] branch main updated (a11af8b -> 17607a3)

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 a11af8b [GCC] Fix GCC8.1 and GCC8.2 template dispatch compilation issue (#6893) add 17607a3 Fix bug of

[GitHub] [incubator-tvm] tqchen closed issue #6884: BUG in CodeGenC::PrintSSAAssign

tqchen closed issue #6884: URL: https://github.com/apache/incubator-tvm/issues/6884 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

[GitHub] [incubator-tvm] tqchen merged pull request #6887: Fix bug of generate-unmatched-brackets in CodeGenC::PrintSSAAssign

tqchen merged pull request #6887: URL: https://github.com/apache/incubator-tvm/pull/6887 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

[incubator-tvm] branch main updated (80ca598 -> a11af8b)

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 80ca598 [TVMC] add cl support in tvmc runner (#6831) add a11af8b [GCC] Fix GCC8.1 and GCC8.2 template

[GitHub] [incubator-tvm] giuseros commented on a change in pull request #6794: [TOPI] Add embedding op and gradient

giuseros commented on a change in pull request #6794: URL: https://github.com/apache/incubator-tvm/pull/6794#discussion_r520667413 ## File path: python/tvm/topi/x86/nn.py ## @@ -69,3 +69,33 @@ def schedule_softmax(outs): s[exp].compute_at(s[softmax], fused_outer_axes)

[GitHub] [incubator-tvm] bernhardklein opened a new issue #6894: [autoTVM][BUG] bitserial dense arm_cpu

bernhardklein opened a new issue #6894: URL: https://github.com/apache/incubator-tvm/issues/6894 The **bitserial dense** operation for **ARM CPU's** is not **auto-tune**-able for larger matrix sizes. For small sizes N=64,125,256,512 it works, but for N=768,1024,2048 it crashes with a

[GitHub] [incubator-tvm] comaniac commented on pull request #6835: [AutoScheduler] Improve tuning with random cost model

comaniac commented on pull request #6835: URL: https://github.com/apache/incubator-tvm/pull/6835#issuecomment-724862117 @merrymercy @jcf94 I increased the measure trial from 2 to 10 to reduce the flaky possibility (please see the latest commit).

[GitHub] [incubator-tvm] piaodangdang commented on issue #6895: run the tutourials file failed cuda is not enable

piaodangdang commented on issue #6895: URL: https://github.com/apache/incubator-tvm/issues/6895#issuecomment-724874031 when i build on window 10 , set use llvm path to llvm, build in visual studio 2019 ,the mentioned is 1>-- 已跳过生成: 项目: cpptest, 配置: Release x64 --

[GitHub] [incubator-tvm] tqchen commented on issue #6895: run the tutourials file failed cuda is not enable

tqchen commented on issue #6895: URL: https://github.com/apache/incubator-tvm/issues/6895#issuecomment-724881876 please open a new thread on https://discuss.tvm.apache.org/ This is an automated message from the Apache Git

[GitHub] [incubator-tvm] tqchen closed issue #6895: run the tutourials file failed cuda is not enable

tqchen closed issue #6895: URL: https://github.com/apache/incubator-tvm/issues/6895 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

[GitHub] [incubator-tvm] tkonolige commented on a change in pull request #6794: [TOPI] Add embedding op and gradient

tkonolige commented on a change in pull request #6794: URL: https://github.com/apache/incubator-tvm/pull/6794#discussion_r520735630 ## File path: python/tvm/topi/x86/nn.py ## @@ -69,3 +69,33 @@ def schedule_softmax(outs): s[exp].compute_at(s[softmax],

[GitHub] [incubator-tvm] comaniac closed issue #6894: [autoTVM][BUG] bitserial dense arm_cpu

comaniac closed issue #6894: URL: https://github.com/apache/incubator-tvm/issues/6894 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

[GitHub] [incubator-tvm] comaniac commented on issue #6894: [autoTVM][BUG] bitserial dense arm_cpu

comaniac commented on issue #6894: URL: https://github.com/apache/incubator-tvm/issues/6894#issuecomment-724854267 At the first glance it looks like the problem in XGBTuner, so trying RandomTuner might workaround it. Let's move the future discussions to https://discuss.tvm.apache.org/.

[GitHub] [incubator-tvm] piaodangdang opened a new issue #6895: run the tutourials file failed cuda is not enable

piaodangdang opened a new issue #6895: URL: https://github.com/apache/incubator-tvm/issues/6895 I build in Ubuntu 1804 cuda 10.1 cuddnn 7.6 I've set use_cuda on but I run the relay_quick_start.ipynb it still tell me cuda is not enable when build, How can I fix it ?

[GitHub] [incubator-tvm] electriclilies commented on a change in pull request #6892: [Relay] Add dynamic SparseToDense

electriclilies commented on a change in pull request #6892: URL: https://github.com/apache/incubator-tvm/pull/6892#discussion_r520719557 ## File path: src/relay/op/dyn/tensor/transform.cc ## @@ -556,6 +556,77 @@ Examples:: .set_attr("TOpPattern", kInjective)

[GitHub] [incubator-tvm] tqchen merged pull request #6860: [TIR] Add spans to all ExprNodes

tqchen merged pull request #6860: URL: https://github.com/apache/incubator-tvm/pull/6860 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

[GitHub] [incubator-tvm] tqchen commented on pull request #6860: [TIR] Add spans to all ExprNodes

tqchen commented on pull request #6860: URL: https://github.com/apache/incubator-tvm/pull/6860#issuecomment-725044052 Thanks @tkonolige @giuseros @jroesch This is an automated message from the Apache Git Service. To respond

[incubator-tvm] branch main updated (17607a3 -> aea74f0)

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 17607a3 Fix bug of generate-unmatched-brackets in CodeGenC::PrintSSAAssign (#6887) add aea74f0 [TIR]

[GitHub] [incubator-tvm] comaniac opened a new pull request #6896: [Backport][TopHub] Bump the versions

comaniac opened a new pull request #6896: URL: https://github.com/apache/incubator-tvm/pull/6896 Backport #6837 to get rid of `-target` warnings in v0.7 release. cc @tqchen @junrushao1994 This is an automated message

[GitHub] [incubator-tvm] comaniac commented on pull request #6896: [Backport][TopHub] Bump the versions

comaniac commented on pull request #6896: URL: https://github.com/apache/incubator-tvm/pull/6896#issuecomment-725018118 @jroesch the CI failed at the rust tasks which seem not related to this change. Would you mind taking a look?

[GitHub] [incubator-tvm] comaniac edited a comment on pull request #6896: [Backport][TopHub] Bump the versions

comaniac edited a comment on pull request #6896: URL: https://github.com/apache/incubator-tvm/pull/6896#issuecomment-725018118 @jroesch the CI failed at the rust tasks which seem not related to this change. Would you mind taking a look?

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r520993062 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r521009413 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[incubator-tvm] branch v0.7 updated: [Backport][TopHub] Bump the versions (#6896)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch v0.7 in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/v0.7 by this push: new efdac94 [Backport][TopHub] Bump the

[GitHub] [incubator-tvm] tqchen merged pull request #6896: [Backport][TopHub] Bump the versions

tqchen merged pull request #6896: URL: https://github.com/apache/incubator-tvm/pull/6896 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

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r520993062 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r520993062 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] jroesch commented on pull request #6885: [Relay][TF] Keep node name in span

jroesch commented on pull request #6885: URL: https://github.com/apache/incubator-tvm/pull/6885#issuecomment-725055722 @lixiaoquan I think we can do this, but I am not sure if overloading the source spans are the right way? perhaps we can sub-class or modify spans for handling whether

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r521009413 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[incubator-tvm] branch main updated: [AutoScheduler] Improve tuning with random cost model (#6835)

This is an automated email from the ASF dual-hosted git repository. lmzheng 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 d03c0c0 [AutoScheduler] Improve tuning

[GitHub] [incubator-tvm] merrymercy merged pull request #6835: [AutoScheduler] Improve tuning with random cost model

merrymercy merged pull request #6835: URL: https://github.com/apache/incubator-tvm/pull/6835 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

[GitHub] [incubator-tvm] lixiaoquan commented on pull request #6885: [Relay][TF] Keep node name in span

lixiaoquan commented on pull request #6885: URL: https://github.com/apache/incubator-tvm/pull/6885#issuecomment-725260027 @jroesch I agree with you. It looks like a makeshift to use SourceName to store node name, I did this because it introduced very little change. I think we can add a

[GitHub] [incubator-tvm] monklof opened a new pull request #6898: add ShapeFunc for tanh

monklof opened a new pull request #6898: URL: https://github.com/apache/incubator-tvm/pull/6898 Enable run static lstm on relay vm by dynamic batch: 1. add ShapeFunc for tanh 2. get in_dim from weights in `_schedule_dense_small_batch ` instead of input in case input's shape's second

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r521009413 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] lsy643 commented on a change in pull request #6864: Qnn for first conv

lsy643 commented on a change in pull request #6864: URL: https://github.com/apache/incubator-tvm/pull/6864#discussion_r521009413 ## File path: tests/python/relay/test_pass_auto_quantize.py ## @@ -148,7 +148,7 @@ def verify_partition(mod, params): assert (

[GitHub] [incubator-tvm] zhiqwang opened a new issue #6897: [Torch] Support aten::hardswish_

zhiqwang opened a new issue #6897: URL: https://github.com/apache/incubator-tvm/issues/6897 > 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

[GitHub] [incubator-tvm] lixiaoquan commented on a change in pull request #6892: [Relay] Add dynamic SparseToDense

lixiaoquan commented on a change in pull request #6892: URL: https://github.com/apache/incubator-tvm/pull/6892#discussion_r521123874 ## File path: src/relay/op/dyn/tensor/transform.cc ## @@ -556,6 +556,77 @@ Examples:: .set_attr("TOpPattern", kInjective)