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 928be03 [Hexagon] Add missing #include (#9968)
add 6d68184 [Doc][Fix] Fix qnn op parameters hint order (#9622)
masahi merged pull request #9622:
URL: https://github.com/apache/tvm/pull/9622
--
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:
AndrewZhaoLuo commented on pull request #9329:
URL: https://github.com/apache/tvm/pull/9329#issuecomment-1016130513
New CI image with updated onnx is (finally up)!
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
yzh119 commented on a change in pull request #9748:
URL: https://github.com/apache/tvm/pull/9748#discussion_r787384558
##
File path: include/tvm/runtime/container/optional.h
##
@@ -93,6 +93,11 @@ class Optional : public ObjectRef {
ICHECK(data_ != nullptr);
return
junrushao1994 commented on a change in pull request #9748:
URL: https://github.com/apache/tvm/pull/9748#discussion_r787379719
##
File path: include/tvm/runtime/container/optional.h
##
@@ -93,6 +93,11 @@ class Optional : public ObjectRef {
ICHECK(data_ != nullptr);
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 da3b63e [Hexagon] Return pathlib.Path from get_hexagon_rpc_path()
(#9969)
add 928be03 [Hexagon] Add missing
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 19717aa [TOPI,x86] Improve performance on int8 conv2d on x86 (#9966)
add da3b63e [Hexagon] Return pathlib.Path
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 904b4ae [CI] Upgrade ONNX (#9965)
add 19717aa [TOPI,x86] Improve performance on int8 conv2d on x86 (#9966)
No new
masahi merged pull request #9968:
URL: https://github.com/apache/tvm/pull/9968
--
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 merged pull request #9969:
URL: https://github.com/apache/tvm/pull/9969
--
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.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from b1bd18e [Runtime][Pipeline executor] Global parameters group name and
runtime modules parameters map. (#9846)
add
masahi merged pull request #9966:
URL: https://github.com/apache/tvm/pull/9966
--
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 closed issue #9511:
URL: https://github.com/apache/tvm/issues/9511
--
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 merged pull request #9965:
URL: https://github.com/apache/tvm/pull/9965
--
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:
jinhongyii opened a new pull request #9975:
URL: https://github.com/apache/tvm/pull/9975
This PR is one of the schedule rule for MetaSchedule.
Co-authored-by: Junru Shao junrushao1...@gmail.com
Co-authored-by: Xiyou Zhou xi...@octoml.ai
Co-authored-by: Bohan Hou
yzh119 opened a new pull request #9974:
URL: https://github.com/apache/tvm/pull/9974
This PR is a fix of #9680 , it checks whether there are undefined variables
in shapes and strides, if so, the buffer parameter is not a simple buffer.
cc @junrushao1994 @vinx13 @shingjan
--
This
areusch commented on pull request #49:
URL: https://github.com/apache/tvm-rfcs/pull/49#issuecomment-1016051672
@Mousius I've added language to explicitly describe our intent to host these
repos underneath Apache in the medium term. PTAL.
--
This is an automated message from the Apache
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787292940
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787288652
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787282472
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787281642
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
srkreddy1238 commented on a change in pull request #52:
URL: https://github.com/apache/tvm-rfcs/pull/52#discussion_r787280802
##
File path: rfcs/0052-OpenCLML-integratio-as-BYOC.md
##
@@ -0,0 +1,90 @@
+- Feature Name: OpenCL ML integration as BYOC
+- Start Date: 2022-01-13
+-
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787280651
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
srkreddy1238 commented on a change in pull request #52:
URL: https://github.com/apache/tvm-rfcs/pull/52#discussion_r787277900
##
File path: rfcs/0052-OpenCLML-integratio-as-BYOC.md
##
@@ -0,0 +1,90 @@
+- Feature Name: OpenCL ML integration as BYOC
+- Start Date: 2022-01-13
+-
driazati commented on issue #123:
URL: https://github.com/apache/tvm/issues/123#issuecomment-1015988085
--
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,
driazati opened a new pull request #9973:
URL: https://github.com/apache/tvm/pull/9973
This will add a comment from GitHub actions after X amount of time has
passed after the last comment on a PR. This should help keep the backlog of PRs
clean by remininding people to do a review or
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787278142
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
driazati commented on issue #123:
URL: https://github.com/apache/tvm/issues/123#issuecomment-1015987975
It has been a while since this PR was updated, @someone please leave a
review or address the outstanding comments
--
This is an automated message from the Apache Git Service.
To
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787277520
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
driazati commented on issue #123:
URL: https://github.com/apache/tvm/issues/123#issuecomment-1015987431
It has been a while since this PR was updated, please leave a review or
address the outstanding comments
--
This is an automated message from the Apache Git Service.
To respond to
driazati commented on issue #123:
URL: https://github.com/apache/tvm/issues/123#issuecomment-1015987262
It has been a while since this PR was updated, please leave a review or
address the outstanding comments
--
This is an automated message from the Apache Git Service.
To respond to
driazati commented on issue #123:
URL: https://github.com/apache/tvm/issues/123#issuecomment-1015987088
It has been a while since this PR was updated, please leave a review or
address the outstanding comments
--
This is an automated message from the Apache Git Service.
To respond to
srkreddy1238 commented on a change in pull request #52:
URL: https://github.com/apache/tvm-rfcs/pull/52#discussion_r787276809
##
File path: rfcs/0052-OpenCLML-integratio-as-BYOC.md
##
@@ -0,0 +1,90 @@
+- Feature Name: OpenCL ML integration as BYOC
+- Start Date: 2022-01-13
+-
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787276842
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
hogepodge commented on a change in pull request #9633:
URL: https://github.com/apache/tvm/pull/9633#discussion_r787276098
##
File path: docs/conf.py
##
@@ -255,6 +255,7 @@ def git_describe_version(original_version):
"introduction.py",
"install.py",
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787276340
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787275962
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787275464
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
srkreddy1238 commented on a change in pull request #52:
URL: https://github.com/apache/tvm-rfcs/pull/52#discussion_r787273682
##
File path: rfcs/0052-OpenCLML-integratio-as-BYOC.md
##
@@ -0,0 +1,90 @@
+- Feature Name: OpenCL ML integration as BYOC
+- Start Date: 2022-01-13
+-
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch cc_reviewers-testing
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 8b4e74c remove merge bot stuff
add 5893d80 Fix target triggers
No new revisions were added by
denise-k opened a new pull request #53:
URL: https://github.com/apache/tvm-rfcs/pull/53
cc @areusch @Mousius @tqchen
--
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
wrongtest commented on pull request #9941:
URL: https://github.com/apache/tvm/pull/9941#issuecomment-1015980480
Also I have question on whether there are solid ways to avoid patch codes at
all. For example, can we prefer to cancel all common terms in summation before
any other rewrites?
driazati opened a new pull request #9972:
URL: https://github.com/apache/tvm/pull/9972
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 reviews from
driazati closed pull request #9936:
URL: https://github.com/apache/tvm/pull/9936
--
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.
areusch pushed a change to branch cc_reviewers-testing
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 96dcee9 Add Action to add cc'ed people as reviewers
add 8b4e74c remove merge bot stuff
No new
srkreddy1238 commented on a change in pull request #52:
URL: https://github.com/apache/tvm-rfcs/pull/52#discussion_r787268420
##
File path: rfcs/0052-OpenCLML-integratio-as-BYOC.md
##
@@ -0,0 +1,90 @@
+- Feature Name: OpenCL ML integration as BYOC
+- Start Date: 2022-01-13
+-
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787267709
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
wrongtest commented on a change in pull request #9941:
URL: https://github.com/apache/tvm/pull/9941#discussion_r787265041
##
File path: src/arith/rewrite_simplify.cc
##
@@ -153,6 +153,16 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
AddNode* op) {
ccjoechou commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787262754
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
driazati opened a new pull request #9971:
URL: https://github.com/apache/tvm/pull/9971
This adds `ci.py` to the docs to make it more clear how to easily build the
docs locally. This also re-arranges CI following the merging of all CI steps to
run concurrently since there's no need to run
ccjoechou commented on pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#issuecomment-1015958031
@areusch - Thanks for replying.
Please see my comments below regarding your questions.
1. Question: device planning, which I think maybe you're doing outside
tkonolige commented on a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787246770
##
File path: src/target/source/codegen_cuda.cc
##
@@ -1051,18 +1051,27 @@ void CodeGenCUDA::PrintWmmaScope(const std::string&
scope, DataType t, const
kparzysz-quic commented on a change in pull request #9964:
URL: https://github.com/apache/tvm/pull/9964#discussion_r787242043
##
File path: src/target/llvm/llvm_module.cc
##
@@ -485,6 +485,11 @@ TVM_REGISTER_GLOBAL("target.llvm_lookup_intrinsic_id")
return
kparzysz-quic commented on pull request #9969:
URL: https://github.com/apache/tvm/pull/9969#issuecomment-1015927243
The reason for this is that if someone wants to initialize
`HEXAGON_RPC_DIR`, like the other globals, they'd have to to that explicitly
with a `pathlib.Path`, but the most
tkonolige edited a comment on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
| Model | Before (ms) | After (ms) |
| --- | --- | ---|
| resnet50 | 5.5282 | 4.7501 |
| inception_v3 | 3.4320 | 3.2994 |
| mobilenetv2 | 1.5239 | 1.1931 |
tkonolige edited a comment on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
| Model | Before (ms) | After (ms) |
| resnet50 | 5.5282 | 4.7501 |
| inception_v3 | 3.4320 | 3.2994 |
| mobilenetv2 | 1.5239 | 1.1931 |
--
This is an
tkonolige commented on pull request #9966:
URL: https://github.com/apache/tvm/pull/9966#issuecomment-1015925994
Model | Before (ms) | After (ms)
resnet50 | 5.5282 | 4.7501
inception_v3 | 3.4320 | 3.2994
mobilenetv2 | 1.5239 | 1.1931
--
This is an automated message from the
mbs-octoml commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787217701
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
spectrometerHBH commented on a change in pull request #9941:
URL: https://github.com/apache/tvm/pull/9941#discussion_r787013464
##
File path: src/arith/rewrite_simplify.cc
##
@@ -153,6 +153,16 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
AddNode* op) {
mbs-octoml commented on a change in pull request #48:
URL: https://github.com/apache/tvm-rfcs/pull/48#discussion_r787217701
##
File path: rfcs/0048-BYOC-Marvell-ML-accelerator-integration.md
##
@@ -0,0 +1,547 @@
+- Feature Name: (fill me in with a unique identifier,
tkonolige commented on a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787217426
##
File path: src/arith/rewrite_simplify.cc
##
@@ -820,6 +820,10 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
FloorDivNode* op) {
cyx-6 commented on pull request #51:
URL: https://github.com/apache/tvm-rfcs/pull/51#issuecomment-1015900542
Thanks @areusch for your questions! Just to provide more context, it's worth
mentioning that the majority of DL compilers built on top of the TVM compiler
(not only the runtime)
kparzysz-quic commented on pull request #9970:
URL: https://github.com/apache/tvm/pull/9970#issuecomment-1015894921
cc: @mehrdadh
--
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
kparzysz-quic commented on pull request #9969:
URL: https://github.com/apache/tvm/pull/9969#issuecomment-1015894759
cc: @mehrdadh
--
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
kparzysz-quic opened a new pull request #9970:
URL: https://github.com/apache/tvm/pull/9970
The Hexagon cmakes have recently become unwieldy due to a complex network of
dependencies between various automatically built components. This was in large
part because of trying to automatically
kparzysz-quic opened a new pull request #9969:
URL: https://github.com/apache/tvm/pull/9969
Type annotations don't do anything, the type conversion needs to be explicit.
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful
kparzysz-quic opened a new pull request #9968:
URL: https://github.com/apache/tvm/pull/9968
This fixes compilation error with libstdc++.
Thanks for contributing to TVM! Please refer to guideline
https://tvm.apache.org/docs/contribute/ for useful information and tips. After
the
driazati commented on pull request #30:
URL: https://github.com/apache/tvm/pull/30#issuecomment-1015889652
hello
--
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
mbs-octoml commented on a change in pull request #9565:
URL: https://github.com/apache/tvm/pull/9565#discussion_r787177088
##
File path: src/relay/backend/aot_executor_codegen.cc
##
@@ -645,32 +632,120 @@ class AOTExecutorCodegen : public MixedModeVisitor {
//
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 4f29562 Enable NPU and CMSIS in ci_qemu (#9957)
add b1bd18e [Runtime][Pipeline executor] Global parameters group
masahi merged pull request #9846:
URL: https://github.com/apache/tvm/pull/9846
--
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 a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787169459
##
File path: python/tvm/relay/op/strategy/cuda.py
##
@@ -641,7 +642,7 @@ def conv3d_strategy_cuda(attrs, inputs, out_type, target):
(N %
masahi edited a comment on pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#issuecomment-1015850768
> Also, remove support for non-float16 tensorcore operations as they cause
large degradation in accuracy
Yeah, I also noticed this implicit downcasting before, I'm in
mbrookhart commented on a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787169612
##
File path: src/arith/rewrite_simplify.cc
##
@@ -820,6 +820,10 @@ PrimExpr RewriteSimplifier::Impl::VisitExpr_(const
FloorDivNode* op) {
masahi commented on a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787169459
##
File path: python/tvm/relay/op/strategy/cuda.py
##
@@ -641,7 +642,7 @@ def conv3d_strategy_cuda(attrs, inputs, out_type, target):
(N %
masahi commented on pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#issuecomment-1015850768
> Also, remove support for non-float16 tensorcore operations as they cause
large degradation in accuracy
Yeah, I also noticed this implicit downcasting before, I'm in favor
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm-rfcs.git.
from 1a3d4f1 [RFC] Integrate LIBXSMM with TVM. (#47)
add 263335f TVM Roadmap RFC (#50)
No new revisions were
areusch commented on pull request #32:
URL: https://github.com/apache/tvm-rfcs/pull/32#issuecomment-1015848390
hey @xiebaiyuan just combing through old RFCs. are you guys still working on
this one?
--
This is an automated message from the Apache Git Service.
To respond to the message,
areusch commented on pull request #50:
URL: https://github.com/apache/tvm-rfcs/pull/50#issuecomment-1015847520
thanks @Mousius @comaniac @denise-k @driazati for the reviews! Merging this
and we'll move forward with the first individual Roadmap RFCs!
--
This is an automated message from
areusch merged pull request #50:
URL: https://github.com/apache/tvm-rfcs/pull/50
--
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:
AndrewZhaoLuo commented on a change in pull request #9965:
URL: https://github.com/apache/tvm/pull/9965#discussion_r787159730
##
File path: Jenkinsfile
##
@@ -46,11 +46,11 @@ import org.jenkinsci.plugins.pipeline.modeldefinition.Utils
// NOTE: these lines are scanned by
mbrookhart commented on a change in pull request #9873:
URL: https://github.com/apache/tvm/pull/9873#discussion_r787157315
##
File path: src/target/source/codegen_cuda.cc
##
@@ -1051,18 +1051,27 @@ void CodeGenCUDA::PrintWmmaScope(const std::string&
scope, DataType t, const
areusch commented on a change in pull request #9565:
URL: https://github.com/apache/tvm/pull/9565#discussion_r787154194
##
File path: src/target/source/codegen_source_base.cc
##
@@ -113,5 +113,60 @@ void CodeGenSourceBase::EndScope(int scope_id) {
indent_ -= 2;
}
+void
areusch commented on a change in pull request #9565:
URL: https://github.com/apache/tvm/pull/9565#discussion_r787153528
##
File path: src/relay/backend/aot_executor_codegen.cc
##
@@ -645,32 +632,120 @@ class AOTExecutorCodegen : public MixedModeVisitor {
//
masahi edited a comment on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1015835747
> Together with that there was performed some refactoring of internal
infrastructure of DNNL plugin
If that's the case, I want this PR to be split into smaller ones.
masahi commented on pull request #9618:
URL: https://github.com/apache/tvm/pull/9618#issuecomment-1015835747
> Together with that there was performed some refactoring of internal
infrastructure of DNNL plugin
If that's the case, I want this PR to be split into smaller ones. It's
masahi commented on a change in pull request #9965:
URL: https://github.com/apache/tvm/pull/9965#discussion_r787142688
##
File path: Jenkinsfile
##
@@ -46,11 +46,11 @@ import org.jenkinsci.plugins.pipeline.modeldefinition.Utils
// NOTE: these lines are scanned by
tkonolige opened a new issue #9967:
URL: https://github.com/apache/tvm/issues/9967
https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/PR-9873/3/pipeline/
`tests/micro/zephyr/test_zephyr_aot.py::test_tflite[qemu_x86]` is failing
with
```
make[3]:
tkonolige opened a new pull request #9966:
URL: https://github.com/apache/tvm/pull/9966
Appended fused operations in cov2d for int8 were computed in a separate loop
from the main conv2d computation:
```
for i in ... parallel
for j in ...
accumulator = 0
for k in ..
masahi commented on issue #9955:
URL: https://github.com/apache/tvm/issues/9955#issuecomment-1015786484
hmm interesting... I believe `unique` op should be well tested so I don't
know why it fails for that example. Can you send a PR with your proposed
solution, along with test cases for
comaniac commented on a change in pull request #9954:
URL: https://github.com/apache/tvm/pull/9954#discussion_r787105243
##
File path: python/tvm/relay/op/nn/_nn.py
##
@@ -1061,6 +1062,83 @@ def compute_space_to_depth(attrs, inputs, out_dtype):
masahi commented on a change in pull request #9954:
URL: https://github.com/apache/tvm/pull/9954#discussion_r787103476
##
File path: python/tvm/relay/op/nn/_nn.py
##
@@ -1061,6 +1062,83 @@ def compute_space_to_depth(attrs, inputs, out_dtype):
masahi commented on a change in pull request #9954:
URL: https://github.com/apache/tvm/pull/9954#discussion_r787103476
##
File path: python/tvm/relay/op/nn/_nn.py
##
@@ -1061,6 +1062,83 @@ def compute_space_to_depth(attrs, inputs, out_dtype):
masahi commented on a change in pull request #8790:
URL: https://github.com/apache/tvm/pull/8790#discussion_r787098337
##
File path: tests/python/frontend/oneflow/test_forward.py
##
@@ -359,7 +359,7 @@ def forward(self, x):
model = Conv2dModel()
model.eval()
-
masahi commented on pull request #8790:
URL: https://github.com/apache/tvm/pull/8790#issuecomment-1015777678
The new image with oneflow installed will go online once
https://github.com/apache/tvm/pull/9965 lands
--
This is an automated message from the Apache Git Service.
To respond to
AndrewZhaoLuo opened a new pull request #9965:
URL: https://github.com/apache/tvm/pull/9965
Closes https://github.com/apache/tvm/issues/9511
Final Pipeline (using the Jenkinsfile in this PR):
https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/ci-docker-staging/209/pipeline
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit fb53dc39868fc842106604a1298c9a27cb36346f
Author: Andrew Luo
AuthorDate: Thu Jan 13 19:07:57 2022 -0800
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
discard c8be9ec jostle ci
discard 55d3a42 Merge branch 'ci-docker-staging' of github.com:apache/tvm
into
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit a5ee1bf68e5812d55ba3972d59df41fa8f57faa7
Author: Andrew Luo
AuthorDate: Thu Jan 13 15:13:26 2022 -0800
This is an automated email from the ASF dual-hosted git repository.
andrewzhaoluo pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 07f9030412d99cf356e512769d0cf6e4e72a0868
Author: Andrew Luo
AuthorDate: Tue Jan 18 11:36:53 2022 -0800
1 - 100 of 172 matches
Mail list logo