[GitHub] [tvm] echuraev commented on a diff in pull request #13408: [OPENCL][TEXTURE] Test case enhancements and fixes for RPC

echuraev commented on code in PR #13408: URL: https://github.com/apache/tvm/pull/13408#discussion_r1024842090 ## tests/python/relay/opencl_texture/test_network.py: ## @@ -0,0 +1,61 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor license

[GitHub] [tvm] d-smirnov commented on a diff in pull request #13369: [usmp] Hill Climb greedy layout size check relaxed

d-smirnov commented on code in PR #13369: URL: https://github.com/apache/tvm/pull/13369#discussion_r1024840349 ## tests/python/contrib/test_ethosu/test_networks.py: ## @@ -142,18 +141,8 @@ def test_networks_with_usmp_and_cascader_wo_striping(accel_type, model_url, work

[GitHub] [tvm] farshidsp opened a new pull request, #13414: [Hexagon] Enable depthwise conv2d NHWC with an HWIO kernel layout

farshidsp opened a new pull request, #13414: URL: https://github.com/apache/tvm/pull/13414 This PR adds support for `depthwise_conv2d_NHWC` with an HWIO kernel layout. @Lunderberg @mehrdadh -- This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [tvm] tvm-bot commented on pull request #13414: [Hexagon] Enable depthwise conv2d NHWC with an HWIO kernel layout

tvm-bot commented on PR #13414: URL: https://github.com/apache/tvm/pull/13414#issuecomment-1318184291 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] tvm-bot commented on pull request #13413: [RUNTIME][OPENCL] OpenCL host pointer support to acheive zero copy

tvm-bot commented on PR #13413: URL: https://github.com/apache/tvm/pull/13413#issuecomment-1318167317 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] srkreddy1238 opened a new pull request, #13413: [RUNTIME][OPENCL] OpenCL host pointer support to acheive zero copy

srkreddy1238 opened a new pull request, #13413: URL: https://github.com/apache/tvm/pull/13413 OpenCL supports device memory access to host by memory mapping. OpenCL flag "CL_MEM_ALLOC_HOST_PTR" enable this while creating a memory object. We enable this feature via compilation setting

[GitHub] [tvm] Hzfengsy commented on a diff in pull request #13406: [MetaSchedule][Fix] Fix Empty Run Time Issue when Benchmarking Result

Hzfengsy commented on code in PR #13406: URL: https://github.com/apache/tvm/pull/13406#discussion_r1024799360 ## src/meta_schedule/measure_callback/update_cost_model.cc: ## @@ -42,7 +42,8 @@ class UpdateCostModelNode : public MeasureCallbackNode {

[GitHub] [tvm] chunit-quic commented on pull request #13402: [Relay][Frontend] Span filling common API

chunit-quic commented on PR #13402: URL: https://github.com/apache/tvm/pull/13402#issuecomment-1318120438 @FrozenGene @areusch @mbs-octoml Tag reviewers in the forum thread and previously reverted PR. It would be a big help to have your advices. Thank you! :D -- This is an

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

chunit-quic commented on code in PR #13402: URL: https://github.com/apache/tvm/pull/13402#discussion_r1024777157 ## python/tvm/relay/frontend/common.py: ## @@ -997,3 +1003,135 @@ def try_resolve_var_to_const(x, graph_params): return _op.const(value, dtype)

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

chunit-quic commented on code in PR #13402: URL: https://github.com/apache/tvm/pull/13402#discussion_r1024777388 ## python/tvm/relay/frontend/common.py: ## @@ -304,13 +306,17 @@ def __init__(self): self.const_ctr = 1 self.in_padding = False -def

[GitHub] [tvm] quic-sanirudh commented on pull request #13256: [Hexagon] Add HVX quant conv2d implementation

quic-sanirudh commented on PR #13256: URL: https://github.com/apache/tvm/pull/13256#issuecomment-1318072797 @csullivan @cconvey Could you please help in reviewing this patch when you get a chance, thanks. -- This is an automated message from the Apache Git Service. To respond to the

[tvm] branch main updated (59abd9e106 -> ad5c811411)

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 59abd9e106 [Build] Fix MSVC compile option /bigobj (#13411) add ad5c811411 [TIR] Unify index data type when

[GitHub] [tvm] junrushao merged pull request #13327: [TIR] Unify index data type when creating prim func

junrushao merged PR #13327: URL: https://github.com/apache/tvm/pull/13327 -- 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] yuwenjun1988 opened a new issue, #13412: [Bug] [BYOC] After partitioning through BYOC, the constant memory in the operator in the model is out of order

yuwenjun1988 opened a new issue, #13412: URL: https://github.com/apache/tvm/issues/13412 After partitioning through BYOC, the constant memory in the operator in the model is out of order

[GitHub] [tvm] vinx13 commented on pull request #13411: [Build] Fix MSVC compile option /bigobj

vinx13 commented on PR #13411: URL: https://github.com/apache/tvm/pull/13411#issuecomment-1317855932 this error always happens using default cmake toolchain on windows , `conda build` works fine though that's why it was not captured by CI -- This is an automated message from the Apache

[tvm] branch main updated (eca361de4f -> 59abd9e106)

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 eca361de4f [MetaSchedule] Fix segfault in gradient based scheduler (#13399) add 59abd9e106 [Build] Fix MSVC

[GitHub] [tvm] junrushao merged pull request #13411: [Build] Fix MSVC compile option /bigobj

junrushao merged PR #13411: URL: https://github.com/apache/tvm/pull/13411 -- 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 (14342a37f5 -> eca361de4f)

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 14342a37f5 [Hexagon] Enable Hexagon User DMA bypass mode (#13381) add eca361de4f [MetaSchedule] Fix segfault in

[GitHub] [tvm] junrushao merged pull request #13399: [MetaSchedule] Fix segfault in gradient based scheduler

junrushao merged PR #13399: URL: https://github.com/apache/tvm/pull/13399 -- 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 nightly-docker-update updated (4806d9088e -> 35e28df7a0)

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 4806d9088e [ci][docker] Nightly Docker image update add 86a5ceec27 [TVMScript] Use tir::Evaluate

[GitHub] [tvm] d-smirnov commented on a diff in pull request #13369: [usmp] Hill Climb greedy layout size check relaxed

d-smirnov commented on code in PR #13369: URL: https://github.com/apache/tvm/pull/13369#discussion_r1024613292 ## tests/python/contrib/test_ethosu/test_networks.py: ## @@ -142,18 +141,8 @@ def test_networks_with_usmp_and_cascader_wo_striping(accel_type, model_url, work

[GitHub] [tvm] d-smirnov commented on a diff in pull request #13369: [usmp] Hill Climb greedy layout size check relaxed

d-smirnov commented on code in PR #13369: URL: https://github.com/apache/tvm/pull/13369#discussion_r1024613292 ## tests/python/contrib/test_ethosu/test_networks.py: ## @@ -142,18 +141,8 @@ def test_networks_with_usmp_and_cascader_wo_striping(accel_type, model_url, work

[GitHub] [tvm] saurabh-shandilya commented on issue #13296: [Bug] TVM generates wrong results for ssd300_vgg16

saurabh-shandilya commented on issue #13296: URL: https://github.com/apache/tvm/issues/13296#issuecomment-1317799286 @masahi I moved to the linux build, so nothing more to be done on this. Thanks for quick resolution on this one. -- This is an automated message from the Apache Git

[GitHub] [tvm] driazati closed issue #11914: [ci] Periodically trigger a repository scan on Jenkins

driazati closed issue #11914: [ci] Periodically trigger a repository scan on Jenkins URL: https://github.com/apache/tvm/issues/11914 -- 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

[GitHub] [tvm] driazati closed issue #11916: [ci] tvm-bot rerun didn't trigger

driazati closed issue #11916: [ci] tvm-bot rerun didn't trigger URL: https://github.com/apache/tvm/issues/11916 -- 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] driazati commented on issue #12004: [Flaky Test] `tests/python/frontend/tensorflow/test_forward.py::test_forward_rint`

driazati commented on issue #12004: URL: https://github.com/apache/tvm/issues/12004#issuecomment-1317735179 This hasn't come up lately afaik, cautiously closing -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] driazati closed issue #12004: [Flaky Test] `tests/python/frontend/tensorflow/test_forward.py::test_forward_rint`

driazati closed issue #12004: [Flaky Test] `tests/python/frontend/tensorflow/test_forward.py::test_forward_rint` URL: https://github.com/apache/tvm/issues/12004 -- 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] driazati commented on issue #11964: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_all_reduce_funcs[llvm]`

driazati commented on issue #11964: URL: https://github.com/apache/tvm/issues/11964#issuecomment-1317735027 This hasn't come up lately afaik, cautiously closing -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] driazati closed issue #11964: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_all_reduce_funcs[llvm]`

driazati closed issue #11964: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_all_reduce_funcs[llvm]` URL: https://github.com/apache/tvm/issues/11964 -- 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] areusch commented on issue #5765: Feature-request: State-of-art Yolo v4 Detector

areusch commented on issue #5765: URL: https://github.com/apache/tvm/issues/5765#issuecomment-1317731387 closing due to inactivity -- 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

[GitHub] [tvm] areusch closed issue #5765: Feature-request: State-of-art Yolo v4 Detector

areusch closed issue #5765: Feature-request: State-of-art Yolo v4 Detector URL: https://github.com/apache/tvm/issues/5765 -- 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 closed issue #12021: [Flaky Test] `tests/python/frontend/tflite/test_forward.py::test_all_unary_elemwise`

driazati closed issue #12021: [Flaky Test] `tests/python/frontend/tflite/test_forward.py::test_all_unary_elemwise` URL: https://github.com/apache/tvm/issues/12021 -- 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] driazati commented on issue #12021: [Flaky Test] `tests/python/frontend/tflite/test_forward.py::test_all_unary_elemwise`

driazati commented on issue #12021: URL: https://github.com/apache/tvm/issues/12021#issuecomment-1317731235 This hasn't come up lately afaik, closing for now -- 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] driazati closed issue #12012: [Flaky Test] `tests/python/frontend/pytorch/test_forward.py::test_argsort`

driazati closed issue #12012: [Flaky Test] `tests/python/frontend/pytorch/test_forward.py::test_argsort` URL: https://github.com/apache/tvm/issues/12012 -- 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] [tvm] driazati commented on issue #12012: [Flaky Test] `tests/python/frontend/pytorch/test_forward.py::test_argsort`

driazati commented on issue #12012: URL: https://github.com/apache/tvm/issues/12012#issuecomment-1317730539 This hasn't come up lately afaik, cautiously closing -- 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] driazati commented on issue #12062: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_qlinearadd[cuda]`

driazati commented on issue #12062: URL: https://github.com/apache/tvm/issues/12062#issuecomment-1317725862 Haven't seen this lately -- 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

[GitHub] [tvm] driazati closed issue #12062: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_qlinearadd[cuda]`

driazati closed issue #12062: [Flaky Test] `tests/python/frontend/onnx/test_forward.py::test_qlinearadd[cuda]` URL: https://github.com/apache/tvm/issues/12062 -- 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] [tvm] areusch commented on issue #5464: [OpenCL] `directly 4 8 bit int in integer` causes compiling error

areusch commented on issue #5464: URL: https://github.com/apache/tvm/issues/5464#issuecomment-1317724767 closing this issue since there is no reproduction and it is over 2 years old. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [tvm] areusch closed issue #5464: [OpenCL] `directly 4 8 bit int in integer` causes compiling error

areusch closed issue #5464: [OpenCL] `directly 4 8 bit int in integer` causes compiling error URL: https://github.com/apache/tvm/issues/5464 -- 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] Lunderberg closed issue #8842: [Test][Possible flaky test] QEMU timeout on zephyr test_relay

Lunderberg closed issue #8842: [Test][Possible flaky test] QEMU timeout on zephyr test_relay URL: https://github.com/apache/tvm/issues/8842 -- 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] Lunderberg commented on issue #8842: [Test][Possible flaky test] QEMU timeout on zephyr test_relay

Lunderberg commented on issue #8842: URL: https://github.com/apache/tvm/issues/8842#issuecomment-1317724359 Test re-enabled in #11362, and running. -- 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] [tvm] driazati commented on issue #12158: [Docs] The documentation section "Install from Source" doesn't describe how to run Python tests

driazati commented on issue #12158: URL: https://github.com/apache/tvm/issues/12158#issuecomment-1317724225 We have a separate section on running tests inside the contributor docs since the install directions are more geared towards people who want to just start using TVM:

[GitHub] [tvm] driazati closed issue #12158: [Docs] The documentation section "Install from Source" doesn't describe how to run Python tests

driazati closed issue #12158: [Docs] The documentation section "Install from Source" doesn't describe how to run Python tests URL: https://github.com/apache/tvm/issues/12158 -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] driazati closed issue #12181: [RFC][Tracking Issue] Name mangling in IRModules

driazati closed issue #12181: [RFC][Tracking Issue] Name mangling in IRModules URL: https://github.com/apache/tvm/issues/12181 -- 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] driazati commented on issue #12181: [RFC][Tracking Issue] Name mangling in IRModules

driazati commented on issue #12181: URL: https://github.com/apache/tvm/issues/12181#issuecomment-1317720287 Closing since the PR is merged, we can re-open if need be -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the

[GitHub] [tvm] Lunderberg closed issue #8769: [OBNNX] alexnet fail to build

Lunderberg closed issue #8769: [OBNNX] alexnet fail to build URL: https://github.com/apache/tvm/issues/8769 -- 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] driazati closed issue #12235: Develop a tool to keep track of skipped tests in CI

driazati closed issue #12235: Develop a tool to keep track of skipped tests in CI URL: https://github.com/apache/tvm/issues/12235 -- 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

[GitHub] [tvm] driazati commented on issue #12235: Develop a tool to keep track of skipped tests in CI

driazati commented on issue #12235: URL: https://github.com/apache/tvm/issues/12235#issuecomment-1317714115 This is implemented in #12915 -- 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] Lunderberg commented on issue #8728: Possible flakey tests/micro/zephyr/test_zephyr.py "test_relay[mps2_an521]"

Lunderberg commented on issue #8728: URL: https://github.com/apache/tvm/issues/8728#issuecomment-1317710836 From [here](https://github.com/apache/tvm/blob/main/tests/scripts/task_python_microtvm.sh#L27), looks like the tests are re-enabled and running correctly. -- This is an automated

[GitHub] [tvm] Lunderberg closed issue #8728: Possible flakey tests/micro/zephyr/test_zephyr.py "test_relay[mps2_an521]"

Lunderberg closed issue #8728: Possible flakey tests/micro/zephyr/test_zephyr.py "test_relay[mps2_an521]" URL: https://github.com/apache/tvm/issues/8728 -- 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] [tvm] driazati closed issue #12335: [CI Problem] Deduplicate the `retry` function from the Jenkinsfile

driazati closed issue #12335: [CI Problem] Deduplicate the `retry` function from the Jenkinsfile URL: https://github.com/apache/tvm/issues/12335 -- 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] driazati commented on issue #12335: [CI Problem] Deduplicate the `retry` function from the Jenkinsfile

driazati commented on issue #12335: URL: https://github.com/apache/tvm/issues/12335#issuecomment-1317710480 This is implemented now in https://github.com/apache/tvm/blob/main/ci/scripts/jenkins/retry.sh -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] driazati closed issue #12311: [Flaky test] Segfault in `test_runtime_module_load.py::test_combine_module_llvm`

driazati closed issue #12311: [Flaky test] Segfault in `test_runtime_module_load.py::test_combine_module_llvm` URL: https://github.com/apache/tvm/issues/12311 -- 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] [tvm] driazati commented on issue #12311: [Flaky test] Segfault in `test_runtime_module_load.py::test_combine_module_llvm`

driazati commented on issue #12311: URL: https://github.com/apache/tvm/issues/12311#issuecomment-1317709166 This hasn't come up recently, closing -- 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] driazati closed issue #12362: [Bug][Relay] TVM generates input name that cannot be imported with the parser

driazati closed issue #12362: [Bug][Relay] TVM generates input name that cannot be imported with the parser URL: https://github.com/apache/tvm/issues/12362 -- 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] [tvm] driazati commented on issue #12362: [Bug][Relay] TVM generates input name that cannot be imported with the parser

driazati commented on issue #12362: URL: https://github.com/apache/tvm/issues/12362#issuecomment-1317708178 This seems like it's fixed by #13046, if that's not the case we can re-open this issue -- This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [tvm] areusch commented on issue #2975: [RFC][PASS][RUNTIME] Enable Slice on LHS during concat

areusch commented on issue #2975: URL: https://github.com/apache/tvm/issues/2975#issuecomment-1317705314 I'm going to close this issue since there hasn't been any change in a couple years. Feel free to reopen if needed. The Discourse forum is a good place for questions like this too. --

[GitHub] [tvm] areusch closed issue #2975: [RFC][PASS][RUNTIME] Enable Slice on LHS during concat

areusch closed issue #2975: [RFC][PASS][RUNTIME] Enable Slice on LHS during concat URL: https://github.com/apache/tvm/issues/2975 -- 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

[GitHub] [tvm] Lunderberg closed issue #8675: [CI] Determine which gpu tests, if any, can be parallelized, and strategy to do so

Lunderberg closed issue #8675: [CI] Determine which gpu tests, if any, can be parallelized, and strategy to do so URL: https://github.com/apache/tvm/issues/8675 -- 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] Lunderberg commented on issue #8675: [CI] Determine which gpu tests, if any, can be parallelized, and strategy to do so

Lunderberg commented on issue #8675: URL: https://github.com/apache/tvm/issues/8675#issuecomment-1317704212 Closed as the CI performance push was largely completd, would need re-timing for current bottlenecks. -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] Lunderberg closed issue #8611: [TEST] test_roi_align in ONNX frontend tests taking 5+ mins of CI time

Lunderberg closed issue #8611: [TEST] test_roi_align in ONNX frontend tests taking 5+ mins of CI time URL: https://github.com/apache/tvm/issues/8611 -- 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] Lunderberg commented on issue #8611: [TEST] test_roi_align in ONNX frontend tests taking 5+ mins of CI time

Lunderberg commented on issue #8611: URL: https://github.com/apache/tvm/issues/8611#issuecomment-1317699216 Closing, as the CI performance was largely resolved, would need re-timing for further performance. -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] Lunderberg closed issue #8610: [TEST] Full network test cases embedded in frontend tests taking 1hr+ on CI runs

Lunderberg closed issue #8610: [TEST] Full network test cases embedded in frontend tests taking 1hr+ on CI runs URL: https://github.com/apache/tvm/issues/8610 -- 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] [tvm] Lunderberg commented on issue #8610: [TEST] Full network test cases embedded in frontend tests taking 1hr+ on CI runs

Lunderberg commented on issue #8610: URL: https://github.com/apache/tvm/issues/8610#issuecomment-1317699058 Closing, as the CI performance was largely resolved, would need re-timing for further performance. -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] driazati closed issue #12388: [ci] Assert that Jenkinsfile changes also change the timestamp

driazati closed issue #12388: [ci] Assert that Jenkinsfile changes also change the timestamp URL: https://github.com/apache/tvm/issues/12388 -- 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] driazati commented on issue #12388: [ci] Assert that Jenkinsfile changes also change the timestamp

driazati commented on issue #12388: URL: https://github.com/apache/tvm/issues/12388#issuecomment-1317688301 This isn't necessary in all cases anymore -- 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] [tvm] gromero commented on a diff in pull request #13377: [microTVM][Zephyr]Add serial_number test args

gromero commented on code in PR #13377: URL: https://github.com/apache/tvm/pull/13377#discussion_r1024510858 ## apps/microtvm/zephyr/template_project/microtvm_api_server.py: ## @@ -504,42 +506,68 @@ def _cmsis_required(self, project_path: Union[str, pathlib.Path]) -> bool:

[GitHub] [tvm] gromero commented on a diff in pull request #13377: [microTVM][Zephyr]Add serial_number test args

gromero commented on code in PR #13377: URL: https://github.com/apache/tvm/pull/13377#discussion_r1024510858 ## apps/microtvm/zephyr/template_project/microtvm_api_server.py: ## @@ -504,42 +506,68 @@ def _cmsis_required(self, project_path: Union[str, pathlib.Path]) -> bool:

[tvm] branch main updated (a80cdc26e2 -> 14342a37f5)

This is an automated email from the ASF dual-hosted git repository. csullivan pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git from a80cdc26e2 [TIR][Analysis][Arith] Implement basic data-flow analysis (#13130) add 14342a37f5 [Hexagon] Enable

[GitHub] [tvm] csullivan merged pull request #13381: [Hexagon] Enable Hexagon User DMA bypass mode

csullivan merged PR #13381: URL: https://github.com/apache/tvm/pull/13381 -- 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] tvm-bot commented on pull request #13411: [Build] Fix MSVC compile option /bigobj

tvm-bot commented on PR #13411: URL: https://github.com/apache/tvm/pull/13411#issuecomment-1317649442 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] vinx13 opened a new pull request, #13411: [Build] Fix MSVC compile option /bigobj

vinx13 opened a new pull request, #13411: URL: https://github.com/apache/tvm/pull/13411 /bigobj was not correctly added to C++ targets. This caused error using cmake build. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[tvm] branch main updated: [TIR][Analysis][Arith] Implement basic data-flow analysis (#13130)

This is an automated email from the ASF dual-hosted git repository. csullivan 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 a80cdc26e2 [TIR][Analysis][Arith] Implement basic

[GitHub] [tvm] csullivan merged pull request #13130: [TIR][Analysis][Arith] Implement basic data-flow analysis

csullivan merged PR #13130: URL: https://github.com/apache/tvm/pull/13130 -- 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] junrushao commented on a diff in pull request #13327: [TIR] Unify index data type when creating prim func

junrushao commented on code in PR #13327: URL: https://github.com/apache/tvm/pull/13327#discussion_r1024384378 ## src/tir/transforms/narrow_datatype.cc: ## @@ -315,65 +265,25 @@ class DataTypeRewriter : public DataTypeLegalizer { return Parent::VisitExpr_(op); } -

[GitHub] [tvm] junrushao commented on a diff in pull request #13327: [TIR] Unify index data type when creating prim func

junrushao commented on code in PR #13327: URL: https://github.com/apache/tvm/pull/13327#discussion_r1024384023 ## src/tir/ir/data_type_rewriter.cc: ## @@ -191,5 +191,352 @@ PrimExpr DataTypeLegalizer::VisitExpr_(const CallNode* op) { return e; } +Stmt

[GitHub] [tvm] driazati commented on pull request #13335: [ci] Split out C++ unittests

driazati commented on PR #13335: URL: https://github.com/apache/tvm/pull/13335#issuecomment-1317474198 Certain GitHub forks are configured in Jenkins to be trusted (e.g. those for people on the oss team), so the extra step to push to apache/tvm isn't necessary. You can see the info here:

[GitHub] [tvm] zxybazh commented on a diff in pull request #13406: [MetaSchedule][Fix] Fix Empty Run Time Issue when Benchmarking Result

zxybazh commented on code in PR #13406: URL: https://github.com/apache/tvm/pull/13406#discussion_r1024302240 ## src/meta_schedule/measure_callback/update_cost_model.cc: ## @@ -42,7 +42,8 @@ class UpdateCostModelNode : public MeasureCallbackNode {

[GitHub] [tvm] mehrdadh commented on pull request #13377: [microTVM][Zephyr]Add serial_number test args

mehrdadh commented on PR #13377: URL: https://github.com/apache/tvm/pull/13377#issuecomment-1317388951 cc @areusch @guberti for review -- 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] AndrewZhaoLuo commented on issue #8577: [Python] Support Python 3.9.X+

AndrewZhaoLuo commented on issue #8577: URL: https://github.com/apache/tvm/issues/8577#issuecomment-1317375151 You can use 3.9, however some parts of TVM might not work (e.g. hybridscript). -- This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [tvm] mehrdadh commented on pull request #12931: [Hexagon] 8 bit lut using tvm script for elemwise operators

mehrdadh commented on PR #12931: URL: https://github.com/apache/tvm/pull/12931#issuecomment-1317350771 You need to rebase with main since there has been some changes in the CI -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [tvm] yelite commented on a diff in pull request #13399: [MetaSchedule] Fix segfault in gradient based scheduler

yelite commented on code in PR #13399: URL: https://github.com/apache/tvm/pull/13399#discussion_r1024267757 ## tests/python/unittest/test_meta_schedule_task_scheduler.py: ## @@ -352,10 +353,85 @@ def test_meta_schedule_task_scheduler_multiple_gradient_based(): )

[GitHub] [tvm] ashutosh-arm commented on a diff in pull request #13410: [ETHOSN] Add support for experimental compiler option

ashutosh-arm commented on code in PR #13410: URL: https://github.com/apache/tvm/pull/13410#discussion_r1024263552 ## src/relay/backend/contrib/ethosn/codegen.cc: ## @@ -713,9 +713,17 @@ runtime::ethosn::OrderedCompiledNetwork EthosnCompiler::CompileEthosnFunc(const auto

[GitHub] [tvm] mehrdadh merged pull request #13404: [Hexagon] Fix TIR vrmpy tensorization

mehrdadh merged PR #13404: URL: https://github.com/apache/tvm/pull/13404 -- 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: [Hexagon] Fix TIR vrmpy tensorization (#13404)

This is an automated email from the ASF dual-hosted git repository. mehrdadh 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 b4d4b82dbb [Hexagon] Fix TIR vrmpy tensorization

[GitHub] [tvm] ashutosh-arm commented on a diff in pull request #13407: [ACL] Enable int8 data type in QNN ADD

ashutosh-arm commented on code in PR #13407: URL: https://github.com/apache/tvm/pull/13407#discussion_r1024260209 ## src/runtime/contrib/arm_compute_lib/acl_utils.cc: ## @@ -130,6 +130,8 @@ arm_compute::DataType MakeACLDataType(const DLDataType& data_type) { return

[GitHub] [tvm] mehrdadh commented on pull request #13335: [ci] Split out C++ unittests

mehrdadh commented on PR #13335: URL: https://github.com/apache/tvm/pull/13335#issuecomment-1317335521 @driazati can you push your branch to a TVM branch to test the jenkins changes? -- This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [tvm] csullivan commented on pull request #13401: [TOPI] Update names for pooling ops

csullivan commented on PR #13401: URL: https://github.com/apache/tvm/pull/13401#issuecomment-1317332045 Thanks @abhikran-quic, @leandron, this is merged, -- 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] [tvm] csullivan merged pull request #13401: [TOPI] Update names for pooling ops

csullivan merged PR #13401: URL: https://github.com/apache/tvm/pull/13401 -- 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: [TOPI] Update names for pooling ops (#13401)

This is an automated email from the ASF dual-hosted git repository. csullivan 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 271ad43029 [TOPI] Update names for pooling ops

[GitHub] [tvm] areusch commented on pull request #13362: [OpenCL] Introduce OpenCL wrapper to TVM

areusch commented on PR #13362: URL: https://github.com/apache/tvm/pull/13362#issuecomment-1317312896 We discussed this in the TVM community meeting this morning - Initially we developed support for OpenCL without statically linking to the library; for mobile, need to manually download

[tvm] branch main updated: [ci][tvmbot] Fix spelling error, metionable -> mentionable (#13276)

This is an automated email from the ASF dual-hosted git repository. driazati 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 52739ef8cd [ci][tvmbot] Fix spelling error,

[GitHub] [tvm] driazati merged pull request #13276: [ci][tvmbot] Fix spelling error, metionable -> mentionable

driazati merged PR #13276: URL: https://github.com/apache/tvm/pull/13276 -- 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 pull request #13276: [ci][tvmbot] Fix spelling error, metionable -> mentionable

driazati commented on PR #13276: URL: https://github.com/apache/tvm/pull/13276#issuecomment-1317306045 Ah thanks for catching, I meant to link #13368 -- 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] [tvm] joshherr-quic commented on pull request #12931: [Hexagon] 8 bit lut using tvm script for elemwise operators

joshherr-quic commented on PR #12931: URL: https://github.com/apache/tvm/pull/12931#issuecomment-1317299149 @mehrdadh Hey not sure what's going on with the CI. It's failing at the prepare step. -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] Mousius commented on pull request #13276: [ci][tvmbot] Fix spelling error, metionable -> mentionable

Mousius commented on PR #13276: URL: https://github.com/apache/tvm/pull/13276#issuecomment-1317276348 > Hey @bkmgit, we recently merged a PR #13276 that makes it so you can iterate and test on this PR without needing a committer in the loop, can you rebase this PR to fix the conflicts then

[GitHub] [tvm] bkmgit commented on pull request #13276: [ci][tvmbot] Fix spelling error, metionable -> mentionable

bkmgit commented on PR #13276: URL: https://github.com/apache/tvm/pull/13276#issuecomment-1317269150 @driazati @Mousius Hopefully ok now. -- 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] srkreddy1238 commented on a diff in pull request #13408: [OPENCL][TEXTURE] Test case enhancements and fixes for RPC

srkreddy1238 commented on code in PR #13408: URL: https://github.com/apache/tvm/pull/13408#discussion_r1024208179 ## python/tvm/relay/frontend/tflite.py: ## @@ -1549,7 +1549,7 @@ def convert_gather(self, op): assert axis < data_dim, "Axis out of bounds" if

[tvm] branch main updated (78b53221f8 -> 44ed06ac9f)

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 78b53221f8 [TIR] Remove PrimFuncNode::preflattened_buffer_map (#10940) add 44ed06ac9f [ETHOSN] Relax concatenate

[GitHub] [tvm] leandron merged pull request #13405: [ETHOSN] Relax concatenate offloading requirements

leandron merged PR #13405: URL: https://github.com/apache/tvm/pull/13405 -- 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:

  1   2   >