[GitHub] [tvm] tvm-bot commented on pull request #13591: [LLVM] Fix get tm allow_missing check pos

tvm-bot commented on PR #13591: URL: https://github.com/apache/tvm/pull/13591#issuecomment-1345156932 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] wrongtest-intellif opened a new pull request, #13591: [LLVM] Fix get tm allow_missing check pos

wrongtest-intellif opened a new pull request, #13591: URL: https://github.com/apache/tvm/pull/13591 It seems that `GetOrCreateTargetMachine`'s failure check would be out of `lookupTarget`' nest scope. -- This is an automated message from the Apache Git Service. To respond to the message,

[tvm] branch nightly updated (3af50e0fce -> 0dc26dd870)

This is an automated email from the ASF dual-hosted git repository. github-bot pushed a change to branch nightly in repository https://gitbox.apache.org/repos/asf/tvm.git from 3af50e0fce [TIR][Transform] Keep the allocate buffers order after update buffer allocation location (#13560)

[tvm] branch main updated (02820ad283 -> 0dc26dd870)

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 02820ad283 [FQ2I] Support converting `dense` -> `add` to `qnn.dense` -> `add` -> `requantize` (#13578) add

[GitHub] [tvm] driazati merged pull request #13590: [ci][docker] Allow usage of ECR images in PRs

driazati merged PR #13590: URL: https://github.com/apache/tvm/pull/13590 -- 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] nverke commented on pull request #13557: [TIR] [Hexagon] Add vdmpy intrinsic and transform_layout for tests

nverke commented on PR #13557: URL: https://github.com/apache/tvm/pull/13557#issuecomment-1345057470 Looks great! -- 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] nverke commented on a diff in pull request #13110: [Hexagon] Add a test to show how to use multi input async dma pipelin…

nverke commented on code in PR #13110: URL: https://github.com/apache/tvm/pull/13110#discussion_r1044960977 ## tests/python/contrib/test_hexagon/test_async_dma_pipeline.py: ## @@ -349,5 +449,313 @@ def test_loading_vtcm_for_vrmpy( "async_dma_input":

[GitHub] [tvm] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044938105 ## python/tvm/contrib/micro/meta_schedule/rpc_runner_micro.py: ## @@ -0,0 +1,243 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] mkatanbaf commented on pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on PR #13514: URL: https://github.com/apache/tvm/pull/13514#issuecomment-1344957393 @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] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044938105 ## python/tvm/contrib/micro/meta_schedule/rpc_runner_micro.py: ## @@ -0,0 +1,243 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044937464 ## python/tvm/meta_schedule/relay_integration.py: ## @@ -385,7 +401,9 @@ def compile_relay( config=pass_config, ): if

[GitHub] [tvm] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044937219 ## python/tvm/meta_schedule/relay_integration.py: ## @@ -97,13 +99,16 @@ def _normalize_params( if executor is None: executor =

[GitHub] [tvm] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044936385 ## src/meta_schedule/schedule_rule/schedule_rule.cc: ## @@ -251,6 +251,33 @@ Array ScheduleRule::DefaultHexagon() { }; } +Array ScheduleRule::DefaultMicro() { +

[GitHub] [tvm] mkatanbaf commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

mkatanbaf commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1044936260 ## python/tvm/contrib/micro/meta_schedule/local_builder_micro.py: ## @@ -0,0 +1,83 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] tvm-bot commented on pull request #13590: [ci][test] Use Docker images from PR build

tvm-bot commented on PR #13590: URL: https://github.com/apache/tvm/pull/13590#issuecomment-1344886198 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] areusch commented on a diff in pull request #13402: [Relay][Frontend] Span filling common API

areusch commented on code in PR #13402: URL: https://github.com/apache/tvm/pull/13402#discussion_r1044908822 ## python/tvm/relay/frontend/common.py: ## @@ -997,3 +1002,167 @@ def try_resolve_var_to_const(x, graph_params): return _op.const(value, dtype) return x

[GitHub] [tvm] areusch commented on a diff in pull request #13402: [Relay][Frontend] Span filling common API

areusch commented on code in PR #13402: URL: https://github.com/apache/tvm/pull/13402#discussion_r1044893998 ## src/relay/ir/expr.cc: ## @@ -72,8 +72,8 @@ Constant::Constant(runtime::NDArray data, Span span) { TVM_REGISTER_NODE_TYPE(ConstantNode);

[GitHub] [tvm] driazati closed pull request #13475: [ci] Don't merge PRs with main

driazati closed pull request #13475: [ci] Don't merge PRs with main URL: https://github.com/apache/tvm/pull/13475 -- 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] driazati commented on pull request #13475: [ci] Don't merge PRs with main

driazati commented on PR #13475: URL: https://github.com/apache/tvm/pull/13475#issuecomment-1344856400 Closing for now, we may revisit this later if these kinds of problems are more frequent -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] guberti commented on a diff in pull request #13514: [microTVM] tuning on micro targets with meta-schedule

guberti commented on code in PR #13514: URL: https://github.com/apache/tvm/pull/13514#discussion_r1043299575 ## python/tvm/contrib/micro/meta_schedule/local_builder_micro.py: ## @@ -0,0 +1,83 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] vinx13 commented on pull request #13568: [MetaSchedule] Add decompose point hint for RewriteReductionBlock

vinx13 commented on PR #13568: URL: https://github.com/apache/tvm/pull/13568#issuecomment-1344773179 Closing this as #13579 is a better solution -- 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] [tvm] vinx13 closed pull request #13568: [MetaSchedule] Add decompose point hint for RewriteReductionBlock

vinx13 closed pull request #13568: [MetaSchedule] Add decompose point hint for RewriteReductionBlock URL: https://github.com/apache/tvm/pull/13568 -- 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

[tvm] branch echuraev/enable_cpp_opencl_tests_in_ci updated (3d3ddc3ebb -> e7c93c3b79)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch echuraev/enable_cpp_opencl_tests_in_ci in repository https://gitbox.apache.org/repos/asf/tvm.git discard 3d3ddc3ebb Update version of gpu docker image add e7c93c3b79 Update version of

[GitHub] [tvm] driazati commented on pull request #13400: [OpenCL][CI] Enable OpenCL cpp tests in CI

driazati commented on PR #13400: URL: https://github.com/apache/tvm/pull/13400#issuecomment-1344716828 lgtm assuming CI passes on the /branch jobs -- 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

[tvm] branch echuraev/enable_cpp_opencl_tests_in_ci updated (7b9d302a3c -> 3d3ddc3ebb)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch echuraev/enable_cpp_opencl_tests_in_ci in repository https://gitbox.apache.org/repos/asf/tvm.git discard 7b9d302a3c Try to enable test in CI add b755099cc5 Try to enable test in CI

[GitHub] [tvm] echuraev commented on a diff in pull request #13400: [OpenCL][CI] Enable OpenCL cpp tests in CI

echuraev commented on code in PR #13400: URL: https://github.com/apache/tvm/pull/13400#discussion_r1044768717 ## ci/jenkins/templates/gpu_jenkinsfile.groovy.j2: ## @@ -74,6 +74,14 @@ label: 'Run Java unit tests', ) {% endif %} + sh ( +script: "${docker_run}

[GitHub] [tvm] AndrewZhaoLuo opened a new pull request, #13589: Simplify Consecutive Casts

AndrewZhaoLuo opened a new pull request, #13589: URL: https://github.com/apache/tvm/pull/13589 cc @guberti -- 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] tvm-bot commented on pull request #13589: Simplify Consecutive Casts

tvm-bot commented on PR #13589: URL: https://github.com/apache/tvm/pull/13589#issuecomment-1344613332 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] driazati commented on a diff in pull request #13400: [OpenCL][CI] Enable OpenCL cpp tests in CI

driazati commented on code in PR #13400: URL: https://github.com/apache/tvm/pull/13400#discussion_r1044684769 ## ci/jenkins/templates/gpu_jenkinsfile.groovy.j2: ## @@ -74,6 +74,14 @@ label: 'Run Java unit tests', ) {% endif %} + sh ( +script: "${docker_run}

[tvm] branch echuraev/enable_cpp_opencl_tests_in_ci created (now 7b9d302a3c)

This is an automated email from the ASF dual-hosted git repository. driazati pushed a change to branch echuraev/enable_cpp_opencl_tests_in_ci in repository https://gitbox.apache.org/repos/asf/tvm.git at 7b9d302a3c Try to enable test in CI No new revisions were added by this update.

[GitHub] [tvm-rfcs] Mousius commented on pull request #96: Embedded Rust API RFC

Mousius commented on PR #96: URL: https://github.com/apache/tvm-rfcs/pull/96#issuecomment-1344537878 Heads up, we're working on an iteration on this RFC with more idiomatic Rust  though anyone willing to take a first pass would be appreciated still. -- This is an automated message from

[GitHub] [tvm] tvm-bot commented on pull request #13588: [microNPU] Disable copying weights to SRAM for FullyConnected ops in CopyConstants scheduler

tvm-bot commented on PR #13588: URL: https://github.com/apache/tvm/pull/13588#issuecomment-1344301453 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[GitHub] [tvm] Alexey-Yazev opened a new pull request, #13588: [microNPU] Disable copying weights to SRAM for FullyConnected ops in CopyConstants scheduler

Alexey-Yazev opened a new pull request, #13588: URL: https://github.com/apache/tvm/pull/13588 In Ethos-U, CopyConstants scheduler currently copies weights for all operators. But in Vela, there are a number of scenarios where the weights are not buffered in SRAM, and FullyConnected case is

[GitHub] [tvm] masahi commented on pull request #12684: [Relay] Bug fix in relay.squeeze function for issue #12400

masahi commented on PR #12684: URL: https://github.com/apache/tvm/pull/12684#issuecomment-1344212796 Maybe you haven't updated the submodules? -- 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] padreofthegame commented on pull request #12684: [Relay] Bug fix in relay.squeeze function for issue #12400

padreofthegame commented on PR #12684: URL: https://github.com/apache/tvm/pull/12684#issuecomment-1344195191 Hello @masahi, After rebasing on main branch (git pull --rebase) after quite a while, git tree looks OK but build fails throwing some very weird errors. Is there a different

[tvm] branch main updated (fbb31fefda -> 02820ad283)

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 fbb31fefda [Hexagon] Skip test if "onnx" module not available (#13585) add 02820ad283 [FQ2I] Support converting

[GitHub] [tvm] masahi merged pull request #13578: [FQ2I] Support converting `dense` -> `add` to `qnn.dense` -> `add` -> `requantize`

masahi merged PR #13578: URL: https://github.com/apache/tvm/pull/13578 -- 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-vta] jmluu opened a new pull request, #38: FIX VTAxxxDPI symbols for tsim

jmluu opened a new pull request, #38: URL: https://github.com/apache/tvm-vta/pull/38 Declare VTASimDPI, VTAHostDPI, VTAMemDPI Functions as extern "C" in `tsim_device.cc`; Otherwise they can't be resolved when generating `libvta_hw.so`. -- This is an automated message from the Apache Git

[GitHub] [tvm] github-actions[bot] commented on pull request #13400: [OpenCL][CI] Enable OpenCL cpp tests in CI

github-actions[bot] commented on PR #13400: URL: https://github.com/apache/tvm/pull/13400#issuecomment-1344085181 Failed to re-run CI in https://github.com/apache/tvm/actions/runs/3656268941 ``` Traceback (most recent call last): File

[GitHub] [tvm] echuraev commented on pull request #13400: [OpenCL][CI] Enable OpenCL cpp tests in CI

echuraev commented on PR #13400: URL: https://github.com/apache/tvm/pull/13400#issuecomment-1344084790 @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] jacquesguan commented on pull request #13587: [Frontend] [ONNX] Support sequence_lens of GRU.

jacquesguan commented on PR #13587: URL: https://github.com/apache/tvm/pull/13587#issuecomment-1344068388 Could you please review this PR @masahi? Thanks! -- 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] [tvm] jacquesguan opened a new pull request, #13587: [Frontend] [ONNX] Support sequence_lens of GRU.

jacquesguan opened a new pull request, #13587: URL: https://github.com/apache/tvm/pull/13587 Support convert sequence_lens input of GRU. -- 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] tvm-bot commented on pull request #13587: [Frontend] [ONNX] Support sequence_lens of GRU.

tvm-bot commented on PR #13587: URL: https://github.com/apache/tvm/pull/13587#issuecomment-1344064832 Thanks for contributing to TVM! Please refer to the contributing guidelines https://tvm.apache.org/docs/contribute/ for useful information and tips. Please request code reviews

[tvm] branch main updated: [Hexagon] Skip test if "onnx" module not available (#13585)

This is an automated email from the ASF dual-hosted git repository. leandron 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 fbb31fefda [Hexagon] Skip test if "onnx" module not

[GitHub] [tvm] leandron merged pull request #13585: [Hexagon] Skip test if "onnx" module not available

leandron merged PR #13585: URL: https://github.com/apache/tvm/pull/13585 -- 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] cxx122 closed issue #12569: [Bug] no divide by zero report while te.floordiv(a, b-b)

cxx122 closed issue #12569: [Bug] no divide by zero report while te.floordiv(a, b-b) URL: https://github.com/apache/tvm/issues/12569 -- 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