[GitHub] [tvm] avquicinc opened a new pull request, #12165: Tanh Float16 Slice Op

avquicinc opened a new pull request, #12165: URL: https://github.com/apache/tvm/pull/12165 Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews

[GitHub] [tvm] huajsj closed issue #8596: [RFC][Tracking Issue] Pipeline Executor For Compute graph pipeline

huajsj closed issue #8596: [RFC][Tracking Issue] Pipeline Executor For Compute graph pipeline URL: https://github.com/apache/tvm/issues/8596 -- 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] huajsj commented on issue #8596: [RFC][Tracking Issue] Pipeline Executor For Compute graph pipeline

huajsj commented on issue #8596: URL: https://github.com/apache/tvm/issues/8596#issuecomment-1193049300 all the task done, thanks @comaniac and @masahi for the kindly review, thanks @rebel-shshin for the follow up, close this issue now. -- This is an automated message from the Apache Git

[GitHub] [tvm] huajsj commented on issue #8596: [RFC][Tracking Issue] Pipeline Executor For Compute graph pipeline

huajsj commented on issue #8596: URL: https://github.com/apache/tvm/issues/8596#issuecomment-1193048829 > > > > thanks @masahi for the follow up, I am also looking forward a chance to do a demo after all patch upstream done. > > > > > > > > > Hi @huajsj, do you have any plan to

[tvm] branch nightly-docker-update updated (34c262b3f6 -> 443abc432d)

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 34c262b3f6 [ci][docker] Nightly Docker image update add 8c42a83361 [arith][BugFix] Fix simplify

[tvm] branch last-successful updated (8dafaf3a4d -> 9863cf0d5f)

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 8dafaf3a4d [Adreno] Fix winograd schedule to support prime shapes > 4 (#12157) add a07e18ea4e

[GitHub] [tvm] zxybazh commented on issue #12135: [Bug] Metaschedule nonexistent error message

zxybazh commented on issue #12135: URL: https://github.com/apache/tvm/issues/12135#issuecomment-1192986103 Hi thanks for reporting this issue, I think you may correct the PrimFunc by removing the root block definition and variable binding as follows: ``` @T.prim_func def

[tvm] branch main updated: [QNN] Support different qnn params between in/out tensor in leaky_relu (#12116)

This is an automated email from the ASF dual-hosted git repository. andrewzhaoluo 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 76155c2f3c [QNN] Support different qnn params

[GitHub] [tvm] AndrewZhaoLuo merged pull request #12116: [QNN] Support different qnn params between in/out tensor in leaky_relu

AndrewZhaoLuo merged PR #12116: URL: https://github.com/apache/tvm/pull/12116 -- 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] huajsj commented on a diff in pull request #11599: [Bugfix][Runtime] Fix sched_setaffinity in Android

huajsj commented on code in PR #11599: URL: https://github.com/apache/tvm/pull/11599#discussion_r927954242 ## src/runtime/threading_backend.cc: ## @@ -321,12 +350,25 @@ class ThreadGroup::Impl { } } +#ifndef __hexagon__ + pid_t Tid() { +#if defined(_WIN32) +

[GitHub] [tvm] masahi merged pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

masahi merged PR #11557: URL: https://github.com/apache/tvm/pull/11557 -- 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: [Runtime][PipelineExecutor] Tutorial of using pipeline executor. (#11557)

This is an automated email from the ASF dual-hosted git repository. masahi 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 ecd3c884de [Runtime][PipelineExecutor] Tutorial of

[tvm] branch main updated: [hexagon][testing] Better pytest ID strings (#12154)

This is an automated email from the ASF dual-hosted git repository. kparzysz 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 9863cf0d5f [hexagon][testing] Better pytest ID

[GitHub] [tvm] kparzysz-quic merged pull request #12154: [hexagon][testing] Better pytest ID strings

kparzysz-quic merged PR #12154: URL: https://github.com/apache/tvm/pull/12154 -- 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] cconvey commented on pull request #12164: WIP [hexagon][testing] nonrandom tests

cconvey commented on PR #12164: URL: https://github.com/apache/tvm/pull/12164#issuecomment-1192871314 CC: @Lunderberg CC: @jverma-quic : FYI in case this this is useful to your work -- This is an automated message from the Apache Git Service. To respond to the message, please log

[GitHub] [tvm] cconvey opened a new pull request, #12164: WIP [hexagon][testing] nonrandom tests

cconvey opened a new pull request, #12164: URL: https://github.com/apache/tvm/pull/12164 Add support for populating unit-test input tensors with values other than random. **NOTE** This is WIP because it builds upon https://github.com/apache/tvm/pull/12154 which is not yet merged.

[tvm] branch main updated: [HEXAGON] QCOM hexagon library (qhl) (#12149)

This is an automated email from the ASF dual-hosted git repository. kparzysz 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 a07e18ea4e [HEXAGON] QCOM hexagon library (qhl)

[GitHub] [tvm] kparzysz-quic merged pull request #12149: [HEXAGON] QCOM hexagon library (qhl)

kparzysz-quic merged PR #12149: URL: https://github.com/apache/tvm/pull/12149 -- 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] cconvey commented on pull request #12154: [hexagon][testing] Better pytest ID strings

cconvey commented on PR #12154: URL: https://github.com/apache/tvm/pull/12154#issuecomment-1192760478 @jverma-quic : FYI because you authored one of these files. -- 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] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927795483 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,248 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927795834 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,248 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[tvm] branch ci-docker-staging updated (477d4d668b -> a7e9360064)

This is an automated email from the ASF dual-hosted git repository. leandron pushed a change to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/tvm.git discard 477d4d668b Validating new gpu image add 8bf6cd5800 [TVMC] Fix tvmc run when using rpc (#11757)

[tvm] 01/02: [TFLite][CI] Update TensorFlow dependency to 2.9.1

This is an automated email from the ASF dual-hosted git repository. leandron pushed a commit to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/tvm.git commit cb6f6409a54e0baeac18c6bb434f911343a3f7d1 Author: Leandro Nunes AuthorDate: Mon May 23 11:55:08 2022 +0100

[tvm] 02/02: This is PR #12130.

This is an automated email from the ASF dual-hosted git repository. leandron pushed a commit to branch ci-docker-staging in repository https://gitbox.apache.org/repos/asf/tvm.git commit a7e936006471f70ca2e5a6fbd48bc4e4e65d4239 Author: Leandro Nunes AuthorDate: Fri Jul 22 16:41:03 2022 +0100

[GitHub] [tvm] MoebiusMeow opened a new issue, #12163: [Bug] ConstantOfShape as shape input failed when using "freeze_params=False" option

MoebiusMeow opened a new issue, #12163: URL: https://github.com/apache/tvm/issues/12163 I simply used relay.frontend.from_onnx to import an ONNX model from PyTorch. The code works fine when freeze_params is set to True (default). When I was trying to separate weights from other

[GitHub] [tvm] echuraev commented on a diff in pull request #11878: [Adreno] Add markup pass of relay tensors for static texture planning

echuraev commented on code in PR #11878: URL: https://github.com/apache/tvm/pull/11878#discussion_r927596550 ## tests/python/relay/test_conv2d_nchw_texture.py: ## @@ -435,3 +435,641 @@ def test_conv2d_vgg16_winograd_4d(): graph = build_run_compare(mod, params1, {"data":

[tvm] branch last-successful updated (4a94a94dfc -> 8dafaf3a4d)

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 4a94a94dfc fix T.Ptr[T.void] for packed api roundtrip (#12118) add 8dafaf3a4d [Adreno] Fix winograd

[GitHub] [tvm] 18761692867 opened a new issue, #12162: [Bug] rfactor：use split for same stage, will coredump in tvm 0.6

18761692867 opened a new issue, #12162: URL: https://github.com/apache/tvm/issues/12162 I have a problem today, maybe is a bug in tvm 0.6, my english is poor, i will try my best to describe the problem clearly ^ ^ **the test py :** `def test_rfactor(): shape_in = (4, 64,

[GitHub] [tvm] yincs-intellif closed pull request #12159: [IR] Normalize IntImm signed Integer type

yincs-intellif closed pull request #12159: [IR] Normalize IntImm signed Integer type URL: https://github.com/apache/tvm/pull/12159 -- 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] yincs-intellif opened a new issue, #12161: [Bug] IntImm Node signed integer indicates an error

yincs-intellif opened a new issue, #12161: URL: https://github.com/apache/tvm/issues/12161 Current IntImm Node can't express negative number by hexadecimal. Eg: x = tvm.tir.const(0x, "int32") x.value should be -1 rather than 4294967295 Whether we need to consider this

[GitHub] [tvm] lhutton1 opened a new pull request, #12160: [ETHOSN] Get buffer sizes from the compiled network

lhutton1 opened a new pull request, #12160: URL: https://github.com/apache/tvm/pull/12160 The NPU support library compiler sometimes adds padding to input tensors which means the buffer sizes calculated at runtime can sometimes be smaller than necessary. Instead, buffer sizes are now

[tvm] branch main updated: [Adreno] Fix winograd schedule to support prime shapes > 4 (#12157)

This is an automated email from the ASF dual-hosted git repository. masahi 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 8dafaf3a4d [Adreno] Fix winograd schedule to support

[GitHub] [tvm] masahi merged pull request #12157: [Adreno] Fix winograd schedule to support prime shapes > 4

masahi merged PR #12157: URL: https://github.com/apache/tvm/pull/12157 -- 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 a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

masahi commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927382124 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,248 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927378703 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927379490 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927378703 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927376733 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[tvm] branch last-successful updated (8c42a83361 -> 4a94a94dfc)

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 8c42a83361 [arith][BugFix] Fix simplify input PrimExpr of DetectClipBound (#12150) add 4a94a94dfc fix

[GitHub] [tvm] yincs-intellif opened a new pull request, #12159: [IR] Normalize IntImm signed Integer type

yincs-intellif opened a new pull request, #12159: URL: https://github.com/apache/tvm/pull/12159 This patch normalize signed IntImm node. Eg: x = tvm.tir.const(0x, "int32") x.value should be -1 rather than 4294967295 cc @Hzfengsy -- This is an automated

[tvm] branch last-successful updated (4fc79b5594 -> 8c42a83361)

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 4fc79b5594 [ETHOSN] Supply output tensor to issupported checks (#11944) add 8c42a83361 [arith][BugFix]

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927332299 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor

[GitHub] [tvm] huajsj commented on a diff in pull request #11557: [Runtime][PipelineExecutor] Tutorial of using pipeline executor.

huajsj commented on code in PR #11557: URL: https://github.com/apache/tvm/pull/11557#discussion_r927332299 ## gallery/how_to/work_with_relay/using_pipeline_executor.py: ## @@ -0,0 +1,250 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more contributor