[tvm] branch main updated (8174d082e8 -> c15cc5ef6d)

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 8174d082e8 Add using directives for otherwise hidden virtual functions, NFC (#12561) add c15cc5ef6d [Target] Remove

[GitHub] [tvm] masahi merged pull request #12416: [Target] Remove deprecated parameters from target

masahi merged PR #12416: URL: https://github.com/apache/tvm/pull/12416 -- 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:

[GitHub] [tvm] masahi closed issue #12409: [Bug] _reconstruct_from_deprecated_options creates incorrect executor

masahi closed issue #12409: [Bug] _reconstruct_from_deprecated_options creates incorrect executor URL: https://github.com/apache/tvm/issues/12409 -- 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

[GitHub] [tvm] crawlingcub commented on a diff in pull request #12563: [PyTorch][Fix] Fix for numerically unstable logsigmoid

crawlingcub commented on code in PR #12563: URL: https://github.com/apache/tvm/pull/12563#discussion_r953315817 ## tests/python/frontend/pytorch/test_forward.py: ## @@ -814,6 +814,14 @@ def test_forward_log_sigmoid(): verify_model(torch.nn.LogSigmoid().eval(),

[GitHub] [tvm] masahi commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

masahi commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953313110 ## python/tvm/tir/tensor_intrin/cuda.py: ## @@ -699,18 +697,18 @@ def wmma_sync_desc(a: T.handle, b: T.handle, c: T.handle) -> None: @T.prim_func def

[GitHub] [tvm] masahi commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

masahi commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953313110 ## python/tvm/tir/tensor_intrin/cuda.py: ## @@ -699,18 +697,18 @@ def wmma_sync_desc(a: T.handle, b: T.handle, c: T.handle) -> None: @T.prim_func def

[GitHub] [tvm] masahi commented on a diff in pull request #12563: [PyTorch][Fix] Fix for numerically unstable logsigmoid

masahi commented on code in PR #12563: URL: https://github.com/apache/tvm/pull/12563#discussion_r953303116 ## tests/python/frontend/pytorch/test_forward.py: ## @@ -814,6 +814,14 @@ def test_forward_log_sigmoid(): verify_model(torch.nn.LogSigmoid().eval(),

[GitHub] [tvm] masahi commented on a diff in pull request #12563: [PyTorch][Fix] Fix for numerically unstable logsigmoid

masahi commented on code in PR #12563: URL: https://github.com/apache/tvm/pull/12563#discussion_r953302670 ## tests/python/frontend/pytorch/test_forward.py: ## @@ -814,6 +814,14 @@ def test_forward_log_sigmoid(): verify_model(torch.nn.LogSigmoid().eval(),

[GitHub] [tvm] driazati commented on pull request #12414: [ci] Default to n=2 for test parallelism

driazati commented on PR #12414: URL: https://github.com/apache/tvm/pull/12414#issuecomment-1225142419 @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

[GitHub] [tvm] alter-xp commented on pull request #12534: [Docker][CI][RISC-V] Build riscv-isa-sim (spike) in ci_riscv Docker image to enable RISC-V unit testing

alter-xp commented on PR #12534: URL: https://github.com/apache/tvm/pull/12534#issuecomment-1225141228 @areusch Currently, there is only one Xuantie compiler in ci_riscv. I ignored the situation of baremetal before. I can add it in image. But It seems better to add it directly to this pr

[GitHub] [tvm] Hzfengsy commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

Hzfengsy commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953250784 ## python/tvm/tir/schedule/schedule.py: ## @@ -2092,9 +2092,9 @@ def before_tensorize( @T.prim_func def mma_desc(a: T.handle, b: T.handle, c:

[GitHub] [tvm] crawlingcub commented on issue #12524: [Bug] Lower Accuracy with a model compared to pytorch

crawlingcub commented on issue #12524: URL: https://github.com/apache/tvm/issues/12524#issuecomment-1225060994 Hi, I added the new test. All the sigmoid tests pass (locally) with the new change. Can you review? -- This is an automated message from the Apache Git Service. To respond to

[GitHub] [tvm] yincs-intellif commented on pull request #12450: [TIR][Schedule] enhance compute_at primitive to choose proper position

yincs-intellif commented on PR #12450: URL: https://github.com/apache/tvm/pull/12450#issuecomment-1225046736 > Hey sorry for the late reply! Happy to do another round of review tomorrow! @junrushao Hi, I don't receive any feedback information. Did I miss something? -- This is an

[GitHub] [tvm] junrushao commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

junrushao commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953223935 ## python/tvm/tir/schedule/schedule.py: ## @@ -2092,9 +2092,9 @@ def before_tensorize( @T.prim_func def mma_desc(a: T.handle, b: T.handle,

[GitHub] [tvm] TejashShah commented on pull request #12537: [Adreno] Change compute/schedule for ToMixedPrecision pass

TejashShah commented on PR #12537: URL: https://github.com/apache/tvm/pull/12537#issuecomment-1225044668 cc @AndrewZhaoLuo @mbrookhart -- 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

[GitHub] [tvm] shingjan opened a new issue, #12566: [Bug] [TIR] float infinity not supported in TIR with CUDA target

shingjan opened a new issue, #12566: URL: https://github.com/apache/tvm/issues/12566 `isinf` is an operator in relay/topi/te. But when we lower relay functions containing `isinf` to cuda, the generated float infinity is not defined and supported, therefore an compilation error on nvcc is

[tvm] branch nightly-docker-update updated (7320d09f95 -> 62b98aee6a)

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 7320d09f95 [ci][docker] Nightly Docker image update add 8e95bba697 Remove mutable defaults in

[GitHub] [tvm] shingjan commented on a diff in pull request #12485: [Relay][Op] embedding_bag operator implementation

shingjan commented on code in PR #12485: URL: https://github.com/apache/tvm/pull/12485#discussion_r953195691 ## python/tvm/relay/frontend/pytorch.py: ## @@ -2242,6 +2243,29 @@ def embedding(self, inputs, input_types): return _op.take(weight, indices.astype("int32"),

[GitHub] [tvm] shingjan commented on a diff in pull request #12485: [Relay][Op] embedding_bag operator implementation

shingjan commented on code in PR #12485: URL: https://github.com/apache/tvm/pull/12485#discussion_r953195691 ## python/tvm/relay/frontend/pytorch.py: ## @@ -2242,6 +2243,29 @@ def embedding(self, inputs, input_types): return _op.take(weight, indices.astype("int32"),

[GitHub] [tvm] shingjan commented on a diff in pull request #12485: [Relay][Op] embedding_bag operator implementation

shingjan commented on code in PR #12485: URL: https://github.com/apache/tvm/pull/12485#discussion_r953194878 ## python/tvm/relay/frontend/pytorch.py: ## @@ -3919,7 +3950,8 @@ def _handel_nested_input(inputs): out_names = _get_output_names(op_node)

[GitHub] [tvm] shingjan commented on a diff in pull request #12485: [Relay][Op] embedding_bag operator implementation

shingjan commented on code in PR #12485: URL: https://github.com/apache/tvm/pull/12485#discussion_r953194878 ## python/tvm/relay/frontend/pytorch.py: ## @@ -3919,7 +3950,8 @@ def _handel_nested_input(inputs): out_names = _get_output_names(op_node)

[GitHub] [tvm] jwfromm commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

jwfromm commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953188945 ## python/tvm/tir/schedule/schedule.py: ## @@ -2092,9 +2092,9 @@ def before_tensorize( @T.prim_func def mma_desc(a: T.handle, b: T.handle, c:

[GitHub] [tvm] junrushao commented on a diff in pull request #12564: [Runtime] Change default alignment to 64 bits.

junrushao commented on code in PR #12564: URL: https://github.com/apache/tvm/pull/12564#discussion_r953186348 ## python/tvm/tir/schedule/schedule.py: ## @@ -2092,9 +2092,9 @@ def before_tensorize( @T.prim_func def mma_desc(a: T.handle, b: T.handle,

[GitHub] [tvm] mehrdadh opened a new pull request, #12565: [Hexagon] Fix missing pytest import

mehrdadh opened a new pull request, #12565: URL: https://github.com/apache/tvm/pull/12565 Fix missing `import pytest` in a test file. cc @driazati -- 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

[tvm] branch last-successful updated (4d104e5ec6 -> 8c23469e20)

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 4d104e5ec6 [ETHOSN] Add support for special indices of Reshape (#12556) add 8c23469e20 [MicroTVM] add

[tvm] branch last-successful updated (1d71c1b4aa -> 4d104e5ec6)

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 1d71c1b4aa [skip ci][ci] Mark more ethosu tests with xfail (#12560) add 99b9b74b12 [CI] Remove Vela

[GitHub] [tvm-rfcs] sunggg commented on a diff in pull request #89: [RFC] Relax Upstreaming

sunggg commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r953154984 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[GitHub] [tvm-rfcs] sunggg commented on a diff in pull request #89: [RFC] Relax Upstreaming

sunggg commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r953154506 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[tvm] branch main updated (13ebbfb37f -> 8174d082e8)

This is an automated email from the ASF dual-hosted git repository. kparzysz pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 13ebbfb37f Replace std::result_of (deprecated in C++17) with std::invoke_result, NFC (#12562) add 8174d082e8 Add

[GitHub] [tvm] kparzysz-quic merged pull request #12561: Add using directives for otherwise hidden virtual functions, NFC

kparzysz-quic merged PR #12561: URL: https://github.com/apache/tvm/pull/12561 -- 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:

[GitHub] [tvm] farshidsp commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

farshidsp commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r953130711 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,13 +56,16 @@ def _compose(args, decs): requires_hexagon_toolchain =

[GitHub] [tvm] areusch commented on issue #12538: [Bug] [microTVM] time_evaluator occasionally gives incorrect values

areusch commented on issue #12538: URL: https://github.com/apache/tvm/issues/12538#issuecomment-1224897113 iirc we made some cleanups to TVMPlatformTimerStop() a few months ago. i thought it was due to updating to Zephyr 2.7; i wonder if that introduced this regression, or if it was here

[tvm] branch last-successful updated (da5836f230 -> 1d71c1b4aa)

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 da5836f230 [AutoTVM] Add support for text buffers to ApplyHistoryBest (#12521) add 1d71c1b4aa [skip

[GitHub] [tvm] driazati commented on a diff in pull request #12436: [CI] Assert some unittests are not skipped in CI

driazati commented on code in PR #12436: URL: https://github.com/apache/tvm/pull/12436#discussion_r953102085 ## tests/python/ci/test_ci.py: ## @@ -33,6 +35,168 @@ def parameterize_named(*values): return pytest.mark.parametrize(",".join(keys), [tuple(d.values()) for d in

[GitHub] [tvm] jwfromm commented on pull request #12564: [Runtime] Change default alignment to 64 bits.

jwfromm commented on PR #12564: URL: https://github.com/apache/tvm/pull/12564#issuecomment-1224883458 @tqchen might be worth having you take a look to see if there are any potential problems with this change. -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] jwfromm opened a new pull request, #12564: [Runtime] Change default alignment to 64 bits.

jwfromm opened a new pull request, #12564: URL: https://github.com/apache/tvm/pull/12564 One change made in #5252 (which added support for Hexagon to the runtime) was increasing the byte alignment from 64 to 128. This can cause problems when interacting with `dlpack`. For example

[GitHub] [tvm] mehrdadh commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

mehrdadh commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r953100120 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,13 +56,16 @@ def _compose(args, decs): requires_hexagon_toolchain =

[tvm] branch main updated (8c23469e20 -> 13ebbfb37f)

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 8c23469e20 [MicroTVM] add heap-size to project options (#12390) add 13ebbfb37f Replace std::result_of (deprecated

[GitHub] [tvm] junrushao merged pull request #12562: Replace std::result_of (deprecated in C++17) with std::invoke_result,…

junrushao merged PR #12562: URL: https://github.com/apache/tvm/pull/12562 -- 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:

[GitHub] [tvm] driazati commented on a diff in pull request #12509: [Target] Add target_device_type attribute to override default device_type

driazati commented on code in PR #12509: URL: https://github.com/apache/tvm/pull/12509#discussion_r953091382 ## include/tvm/target/target_kind.h: ## @@ -102,7 +102,7 @@ class TargetKindNode : public Object { void VisitAttrs(AttrVisitor* v) { v->Visit("name", ); -

[GitHub] [tvm] areusch commented on a diff in pull request #12509: [Target] Add target_device_type attribute to override default device_type

areusch commented on code in PR #12509: URL: https://github.com/apache/tvm/pull/12509#discussion_r953079921 ## include/tvm/target/target_kind.h: ## @@ -470,7 +470,8 @@ constexpr const char* kRelayToTIR = "RelayToTIR"; .add_attr_option("model") \

[GitHub] [tvm] areusch commented on pull request #12534: [Docker][CI][RISC-V] Build riscv-isa-sim (spike) in ci_riscv Docker image to enable RISC-V unit testing

areusch commented on PR #12534: URL: https://github.com/apache/tvm/pull/12534#issuecomment-1224801969 @alter-xp @PhilippvK gotcha--it's fine to have two toolchains in ci_riscv if they have a defined purpose. could we document that purpose in the install scripts? -- This is an automated

[GitHub] [tvm] areusch commented on a diff in pull request #12534: [Docker][CI][RISC-V] Build riscv-isa-sim (spike) in ci_riscv Docker image to enable RISC-V unit testing

areusch commented on code in PR #12534: URL: https://github.com/apache/tvm/pull/12534#discussion_r953071105 ## python/tvm/micro/testing/aot_test_utils.py: ## @@ -65,6 +65,17 @@ }, ) +AOT_SPIKE_RUNNER = AOTTestRunner( Review Comment: ah gotcha; it's probably fine to

[GitHub] [tvm] masahi commented on issue #12524: [Bug] Lower Accuracy with a model compared to pytorch

masahi commented on issue #12524: URL: https://github.com/apache/tvm/issues/12524#issuecomment-1224790611 You can try, for example `pytest tests/python/frontend/pytorch/test_forward.py -k log_sigmoid -s` -- This is an automated message from the Apache Git Service. To respond to the

[tvm] branch main updated (4d104e5ec6 -> 8c23469e20)

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.git from 4d104e5ec6 [ETHOSN] Add support for special indices of Reshape (#12556) add 8c23469e20 [MicroTVM] add heap-size to

[GitHub] [tvm] areusch commented on pull request #12390: [MicroTVM] add heap-size to project options

areusch commented on PR #12390: URL: https://github.com/apache/tvm/pull/12390#issuecomment-1224790066 thanks @mkatanbaf ! -- 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.

[GitHub] [tvm] areusch merged pull request #12390: [MicroTVM] add heap-size to project options

areusch merged PR #12390: URL: https://github.com/apache/tvm/pull/12390 -- 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:

[GitHub] [tvm] crawlingcub commented on issue #12524: [Bug] Lower Accuracy with a model compared to pytorch

crawlingcub commented on issue #12524: URL: https://github.com/apache/tvm/issues/12524#issuecomment-1224778517 ok, naive question: how do i run a specific test locally? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use

[GitHub] [tvm] lhutton1 commented on pull request #12558: [microNPU] Force compute_cycles_hint to be interpreted as an int64 value

lhutton1 commented on PR #12558: URL: https://github.com/apache/tvm/pull/12558#issuecomment-1224773920 Sounds good, thanks @driazati! -- 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

[GitHub] [tvm] areusch commented on a diff in pull request #12512: [bug fix] fix split filter in conv1d and conv2d to avoid empty search space

areusch commented on code in PR #12512: URL: https://github.com/apache/tvm/pull/12512#discussion_r953060785 ## python/tvm/topi/arm_cpu/mprofile/dsp/conv2d.py: ## @@ -120,7 +121,12 @@ def conv2d_nhwc_dsp_compute(cfg, data, kernel, strides, padding, dilation, out_d

[tvm] branch main updated (99b9b74b12 -> 4d104e5ec6)

This is an automated email from the ASF dual-hosted git repository. lukhut pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 99b9b74b12 [CI] Remove Vela from ci_cpu (#12533) add 4d104e5ec6 [ETHOSN] Add support for special indices of Reshape

[GitHub] [tvm] lhutton1 merged pull request #12556: [ETHOSN] Add support for special indices of Reshape

lhutton1 merged PR #12556: URL: https://github.com/apache/tvm/pull/12556 -- 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:

[GitHub] [tvm] masahi commented on issue #12524: [Bug] Lower Accuracy with a model compared to pytorch

masahi commented on issue #12524: URL: https://github.com/apache/tvm/issues/12524#issuecomment-1224757199 hmm maybe argmax got fixed, but the raw outputs should still be different. First, please run the test in

[tvm] branch main updated (1d71c1b4aa -> 99b9b74b12)

This is an automated email from the ASF dual-hosted git repository. leandron pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from 1d71c1b4aa [skip ci][ci] Mark more ethosu tests with xfail (#12560) add 99b9b74b12 [CI] Remove Vela from ci_cpu

[GitHub] [tvm] leandron merged pull request #12533: [CI] Remove Vela from ci_cpu

leandron merged PR #12533: URL: https://github.com/apache/tvm/pull/12533 -- 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:

[GitHub] [tvm] crawlingcub opened a new pull request, #12563: [PyTorch][Fix] Fix for numerically unstable logsigmoid

crawlingcub opened a new pull request, #12563: URL: https://github.com/apache/tvm/pull/12563 Fix for #12524 -- 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

[GitHub] [tvm] kparzysz-quic commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

kparzysz-quic commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r953040326 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,14 +56,19 @@ def _compose(args, decs): requires_hexagon_toolchain =

[GitHub] [tvm] crawlingcub commented on issue #12524: [Bug] Lower Accuracy with a model compared to pytorch

crawlingcub commented on issue #12524: URL: https://github.com/apache/tvm/issues/12524#issuecomment-1224692072 Yes, that fixes it! :) I see exact same accuracy now! Should I raise a PR? -- This is an automated message from the Apache Git Service. To respond to the message, please log on

[GitHub] [tvm] farshidsp commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

farshidsp commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r953020364 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,14 +56,19 @@ def _compose(args, decs): requires_hexagon_toolchain =

[tvm] branch last-successful updated (d271678388 -> da5836f230)

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 d271678388 [CI][AArch64] Skip libgomp failures in integration tests (#12554) add ff46fa15e0 [ETHOSN]

[GitHub] [tvm] kparzysz-quic commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

kparzysz-quic commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r953005947 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,14 +56,19 @@ def _compose(args, decs): requires_hexagon_toolchain =

[GitHub] [tvm-rfcs] YuchenJin commented on a diff in pull request #89: [RFC] Relax Upstreaming

YuchenJin commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r952996763 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[GitHub] [tvm] driazati closed issue #12464: [Flaky Test] `tests/python/frontend/caffe/test_forward.py::test_forward_Alexnet`, `tests/python/frontend/caffe/test_forward.py::test_forward_Inceptionv1`

driazati closed issue #12464: [Flaky Test] `tests/python/frontend/caffe/test_forward.py::test_forward_Alexnet`, `tests/python/frontend/caffe/test_forward.py::test_forward_Inceptionv1` URL: https://github.com/apache/tvm/issues/12464 -- This is an automated message from the Apache Git

[GitHub] [tvm] driazati commented on pull request #12414: [ci] Default to n=2 for test parallelism

driazati commented on PR #12414: URL: https://github.com/apache/tvm/pull/12414#issuecomment-1224554517 @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

[GitHub] [tvm] farshidsp commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

farshidsp commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r952972379 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,14 +56,19 @@ def _compose(args, decs): requires_hexagon_toolchain =

[GitHub] [tvm] farshidsp commented on a diff in pull request #12504: [Hexagon] Add support to run on multiple devices

farshidsp commented on code in PR #12504: URL: https://github.com/apache/tvm/pull/12504#discussion_r952971408 ## python/tvm/contrib/hexagon/pytest_plugin.py: ## @@ -56,14 +56,19 @@ def _compose(args, decs): requires_hexagon_toolchain =

[GitHub] [tvm] driazati commented on pull request #12558: [microNPU] Force compute_cycles_hint to be interpreted as an int64 value

driazati commented on PR #12558: URL: https://github.com/apache/tvm/pull/12558#issuecomment-1224511525 CI should be unblocked by #12560, that will still run the test but it will also ignore failures. We can merge this PR and spot check a few of the CI logs to make sure that the test isn't

[GitHub] [tvm] driazati merged pull request #12560: [skip ci][ci] Mark more ethosu tests with xfail

driazati merged PR #12560: URL: https://github.com/apache/tvm/pull/12560 -- 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:

[tvm] branch main updated (da5836f230 -> 1d71c1b4aa)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from da5836f230 [AutoTVM] Add support for text buffers to ApplyHistoryBest (#12521) add 1d71c1b4aa [skip ci][ci] Mark

[GitHub] [tvm] github-actions[bot] commented on pull request #12560: [skip ci][ci] Mark more ethosu tests with xfail

github-actions[bot] commented on PR #12560: URL: https://github.com/apache/tvm/pull/12560#issuecomment-1224488923 Built docs for commit fbf5997b4f35f7c84654f440c977c35b946e140c can be found [here](https://pr-docs.tlcpack.ai/PR-12560/2/docs/index.html). -- This is an automated

[GitHub] [tvm] kparzysz-quic commented on pull request #12562: Replace std::result_of (deprecated in C++17) with std::invoke_result,…

kparzysz-quic commented on PR #12562: URL: https://github.com/apache/tvm/pull/12562#issuecomment-1224478934 cc: @gbonik -- 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

[GitHub] [tvm] kparzysz-quic opened a new pull request, #12562: Replace std::result_of (deprecated in C++17) with std::invoke_result,…

kparzysz-quic opened a new pull request, #12562: URL: https://github.com/apache/tvm/pull/12562 … NFC -- 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,

[GitHub] [tvm] kparzysz-quic opened a new pull request, #12561: Add using directives for otherwise hidden virtual functions, NFC

kparzysz-quic opened a new pull request, #12561: URL: https://github.com/apache/tvm/pull/12561 This silences warning ``` warning: 'foo' hides overloaded virtual functions [-Woverloaded-virtual] ``` typically caused by overriding only some overloads of `VisitExpr_` from a set

[GitHub] [tvm-rfcs] slyubomirsky commented on a diff in pull request #89: [RFC] Relax Upstreaming

slyubomirsky commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r952934825 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[GitHub] [tvm-rfcs] slyubomirsky commented on a diff in pull request #89: [RFC] Relax Upstreaming

slyubomirsky commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r952934825 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[GitHub] [tvm] driazati opened a new pull request, #12560: [ci] Mark more ethosu tests with xfail

driazati opened a new pull request, #12560: URL: https://github.com/apache/tvm/pull/12560 See #12511 for context. Since more parameterizations are popping up as failed, this disables whole tests rather than specific combinations of parameters. -- This is an automated message from

[GitHub] [tvm-rfcs] slyubomirsky commented on pull request #89: [RFC] Relax Upstreaming

slyubomirsky commented on PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#issuecomment-1224450123 On the point about potentially incorporating symbolic shapes into Relay, I would like to hear more detail about how it can be done with Relay's system of accumulating type constraints

[GitHub] [tvm-rfcs] slyubomirsky commented on a diff in pull request #89: [RFC] Relax Upstreaming

slyubomirsky commented on code in PR #89: URL: https://github.com/apache/tvm-rfcs/pull/89#discussion_r952934825 ## rfcs/0089-relax-upstreaming.md: ## @@ -0,0 +1,701 @@ +- Feature Name: Relax Upstreaming +- Start Date: 2022-08-17 +- RFC PR: 

[GitHub] [tvm] trahman-quic commented on pull request #12559: [TOPI][Hexagon] Add test and schedule for uint8 resize2d

trahman-quic commented on PR #12559: URL: https://github.com/apache/tvm/pull/12559#issuecomment-1224422346 The details for the changes in this [commit ](https://github.com/apache/tvm/pull/12559/commits/8362a560c329e3235ac5e93bfbaadc417e4b6ede) for this PR can be referred to

[GitHub] [tvm] adstraw commented on a diff in pull request #12411: [Hexagon] Asynchronous DMA support

adstraw commented on code in PR #12411: URL: https://github.com/apache/tvm/pull/12411#discussion_r952910319 ## tests/cpp-runtime/hexagon/hexagon_user_dma_tests.cc: ## @@ -0,0 +1,141 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or more contributor

[GitHub] [tvm] AndrewZhaoLuo commented on a diff in pull request #12555: [frontend][onnx]fix pad constant value is none

AndrewZhaoLuo commented on code in PR #12555: URL: https://github.com/apache/tvm/pull/12555#discussion_r952897732 ## python/tvm/relay/frontend/onnx.py: ## @@ -1403,7 +1403,7 @@ def _impl_v2(cls, inputs, attr, params): @classmethod def _impl_v11(cls, inputs, attr,

[GitHub] [tvm] trahman-quic opened a new pull request, #12559: [TOPI][Hexagon] Add test and schedule for uint8 resize2d

trahman-quic opened a new pull request, #12559: URL: https://github.com/apache/tvm/pull/12559 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

[GitHub] [tvm] gigiblender commented on a diff in pull request #12436: [CI] Assert some unittests are not skipped in CI

gigiblender commented on code in PR #12436: URL: https://github.com/apache/tvm/pull/12436#discussion_r952893155 ## tests/scripts/github_skipped_tests_comment.py: ## @@ -0,0 +1,206 @@ +#!/usr/bin/env python3 +# Licensed to the Apache Software Foundation (ASF) under one +# or

[tvm] branch main updated (dd7ae2d3e5 -> da5836f230)

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.git from dd7ae2d3e5 [Relay] Add Rsqrt to SimplifyExpr (#12363) add da5836f230 [AutoTVM] Add support for text buffers to

[GitHub] [tvm] areusch merged pull request #12521: [AutoTVM] Add support for text buffers to ApplyHistoryBest

areusch merged PR #12521: URL: https://github.com/apache/tvm/pull/12521 -- 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:

[GitHub] [tvm] areusch commented on a diff in pull request #12521: [AutoTVM] Add support for text buffers to ApplyHistoryBest

areusch commented on code in PR #12521: URL: https://github.com/apache/tvm/pull/12521#discussion_r952856513 ## python/tvm/autotvm/task/dispatcher.py: ## @@ -30,18 +30,26 @@ from __future__ import absolute_import as _abs +from io import TextIOBase import logging -import

[GitHub] [tvm] github-actions[bot] commented on pull request #12454: [Target] Add Target Parser for Arm(R) Cortex(R) A-Profile CPUs

github-actions[bot] commented on PR #12454: URL: https://github.com/apache/tvm/pull/12454#issuecomment-1224302981 It has been a while since this PR was updated, @u99127 please leave a review or address the outstanding comments. @Mousius if this PR is still a work in progress, please

[GitHub] [tvm] csullivan commented on a diff in pull request #12537: [Adreno] Change compute/schedule for ToMixedPrecision pass

csullivan commented on code in PR #12537: URL: https://github.com/apache/tvm/pull/12537#discussion_r952839198 ## python/tvm/topi/adreno/conv2d_nhwc.py: ## @@ -270,37 +264,27 @@ def schedule_conv2d_NHWC(cfg, s, output): # space definition end # pad_data,

[GitHub] [tvm] lhutton1 opened a new pull request, #12558: [microNPU] Force compute_cycles_hint to be interpreted as an int64 value

lhutton1 opened a new pull request, #12558: URL: https://github.com/apache/tvm/pull/12558 `compute_cycles` can be the size of an int64 value, however it seems that when that value is attached to the IR as a pragma from Python, it is interpreted as an `int`, rather than `int64_t`. This

[GitHub] [tvm] ashutosh-arm opened a new pull request, #12557: [CI][CMSIS-NN] Running tests parallel using pytest-xdist

ashutosh-arm opened a new pull request, #12557: URL: https://github.com/apache/tvm/pull/12557 Introducing -n auto for CMSIS-NN tests to run them parallel with pytest-xdist. This is needed because of additional parameterization done over cpu variants. cc @leandron @lhutton1

[GitHub] [tvm] leandron commented on pull request #12535: [ETHOSN] Add support for Resize

leandron commented on PR #12535: URL: https://github.com/apache/tvm/pull/12535#issuecomment-1224268224 This can be merged once CI is green. -- 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

[GitHub] [tvm] mbrookhart commented on pull request #12363: [Relay] Add Rsqrt to SimplifyExpr

mbrookhart commented on PR #12363: URL: https://github.com/apache/tvm/pull/12363#issuecomment-1224264534 Thanks @AndrewZhaoLuo @junrushao -- 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

[tvm] branch main updated (ff46fa15e0 -> dd7ae2d3e5)

This is an automated email from the ASF dual-hosted git repository. mbrookhart pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from ff46fa15e0 [ETHOSN] Fix requantize output conversion (#12540) add dd7ae2d3e5 [Relay] Add Rsqrt to SimplifyExpr

[GitHub] [tvm] mbrookhart merged pull request #12363: [Relay] Add Rsqrt to SimplifyExpr

mbrookhart merged PR #12363: URL: https://github.com/apache/tvm/pull/12363 -- 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:

[GitHub] [tvm] NicolaLancellotti commented on a diff in pull request #12535: [ETHOSN] Add support for Resize

NicolaLancellotti commented on code in PR #12535: URL: https://github.com/apache/tvm/pull/12535#discussion_r952805038 ## tests/python/contrib/test_ethosn/test_resize.py: ## @@ -0,0 +1,119 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[tvm] branch last-successful updated (383bd41931 -> d271678388)

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 383bd41931 Fix TFLite 2.9 tests (#12130) add 52779f1273 [CMSIS-NN] Pad fusion with QNN Conv2D (#12353)

[GitHub] [tvm] cconvey commented on issue #12511: [Flaky Test] various tests in `tests/python/contrib/test_ethosu/test_codegen.py`

cconvey commented on issue #12511: URL: https://github.com/apache/tvm/issues/12511#issuecomment-1224236581 Another CI failure: ### Tests(s) - `tests/python/contrib/test_ethosu/test_codegen.py::test_binary_add_with_non_4d_shapes[ifm_shape0-ifm2_shape0-ethos-u55-128]` -

[GitHub] [tvm] cconvey commented on issue #12511: [Flaky Test] various tests in `tests/python/contrib/test_ethosu/test_codegen.py`

cconvey commented on issue #12511: URL: https://github.com/apache/tvm/issues/12511#issuecomment-1224235998 Another CI failure: ### Tests(s) - `tests/python/contrib/test_ethosu/test_codegen.py::test_binary_add_with_non_4d_shapes[ifm_shape0-ifm2_shape0-ethos-u55-128]` -

[GitHub] [tvm] cconvey commented on issue #12511: [Flaky Test] various tests in `tests/python/contrib/test_ethosu/test_codegen.py`

cconvey commented on issue #12511: URL: https://github.com/apache/tvm/issues/12511#issuecomment-1224235195 Another CI failure: These tests were found to be flaky (intermittently failing on `main` or failed in a PR with unrelated changes). See [the

[GitHub] [tvm] cconvey commented on issue #12511: [Flaky Test] various tests in `tests/python/contrib/test_ethosu/test_codegen.py`

cconvey commented on issue #12511: URL: https://github.com/apache/tvm/issues/12511#issuecomment-1224234001 Another CI failure: These tests were found to be flaky (intermittently failing on `main` or failed in a PR with unrelated changes). See [the

  1   2   >