[GitHub] [incubator-tvm] ashutoshparkhi commented on issue #6340: Faster RCNN: Unable to compile for CPU because topk fails

ashutoshparkhi commented on issue #6340: URL: https://github.com/apache/incubator-tvm/issues/6340#issuecomment-682355679 While trying to compile it with commit a64feed, compilation goes through. This is an automated message f

[GitHub] [incubator-tvm] zhanghaohit commented on pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

zhanghaohit commented on pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#issuecomment-682351681 > I am wondering whether VTA's graph annotation can be unified into the relay's heterogeneous execution feature: #4178 I think #4178 is for VM, while graph annot

[GitHub] [incubator-tvm] zhanghaohit closed pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

zhanghaohit closed pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125 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] [incubator-tvm] zhanghaohit commented on pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

zhanghaohit commented on pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#issuecomment-682350954 > #4178 This is an automated message from the Apache Git Service. To respond to the message, p

[GitHub] [incubator-tvm] zhanghaohit removed a comment on pull request #6125: [VTA][OpenCL] add device_annot support in graphpack

zhanghaohit removed a comment on pull request #6125: URL: https://github.com/apache/incubator-tvm/pull/6125#issuecomment-682350954 > #4178 This is an automated message from the Apache Git Service. To respond to the me

[GitHub] [incubator-tvm] junrushao1994 removed a comment on pull request #6347: [Target][Codegen] Use target class in all codegens

junrushao1994 removed a comment on pull request #6347: URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-682166368 idk why the CI is retriggered... This is an automated message from the Apache Git Service. T

[incubator-tvm] branch master updated: typo (#6352)

This is an automated email from the ASF dual-hosted git repository. zhic pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new 02b643b typo (#6352) 02b643b is described

[GitHub] [incubator-tvm] zhiics commented on pull request #6352: [Maintenance] Fix typo

zhiics commented on pull request #6352: URL: https://github.com/apache/incubator-tvm/pull/6352#issuecomment-682317858 Thanks @hypercubestart @MarisaKirisame This is an automated message from the Apache Git Service. To respon

[GitHub] [incubator-tvm] zhiics merged pull request #6352: [Maintenance] Fix typo

zhiics merged pull request #6352: URL: https://github.com/apache/incubator-tvm/pull/6352 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 g

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

zhiics commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478822568 ## File path: include/tvm/runtime/vm/bytecode.h ## @@ -204,6 +207,13 @@ struct Instruction { RegName tensor; RegName newshape; } r

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

zhiics commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478821758 ## File path: src/relay/analysis/context_analysis.cc ## @@ -0,0 +1,697 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or m

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

zhiics commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478821957 ## File path: python/tvm/relay/transform/memory_alloc.py ## @@ -66,7 +85,7 @@ def is_reshape_only(func): class ManifestAllocPass(ExprMutator): Revi

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

zhiics commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478821823 ## File path: src/relay/analysis/context_analysis.cc ## @@ -0,0 +1,697 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + * or m

[GitHub] [incubator-tvm] jcf94 commented on a change in pull request #6348: [Ansor][AutoTVM v2.0] Phase 2: Update heavy operations with parallel_for

jcf94 commented on a change in pull request #6348: URL: https://github.com/apache/incubator-tvm/pull/6348#discussion_r478806015 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -322,32 +323,40 @@ Array SketchPolicyNode::GenerateSketches() { } Array Sket

[GitHub] [incubator-tvm] jcf94 commented on a change in pull request #6348: [Ansor][AutoTVM v2.0] Phase 2: Update heavy operations with parallel_for

jcf94 commented on a change in pull request #6348: URL: https://github.com/apache/incubator-tvm/pull/6348#discussion_r478806015 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -322,32 +323,40 @@ Array SketchPolicyNode::GenerateSketches() { } Array Sket

[GitHub] [incubator-tvm] electriclilies opened a new pull request #6353: [RELAY][DYN] Dynamic UpSampling3D Op

electriclilies opened a new pull request #6353: URL: https://github.com/apache/incubator-tvm/pull/6353 This PR implements the dynamic version of the UpSampling3D relay op. After this is merged, we will be able to remove the final infer_value calls from the onnx importer, allowing us to imp

[GitHub] [incubator-tvm] tkonolige commented on pull request #6331: [TESTS] Refactor tests to run on either the GPU or CPU

tkonolige commented on pull request #6331: URL: https://github.com/apache/incubator-tvm/pull/6331#issuecomment-682256268 @tqchen I'm getting a couple errors with CUDA initialization failing. I'm really sure of the cause, but it seems like it might have to do with forking.

[GitHub] [incubator-tvm] hypercubestart opened a new pull request #6352: [Maintenance] Fix typo

hypercubestart opened a new pull request #6352: URL: https://github.com/apache/incubator-tvm/pull/6352 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the

[incubator-tvm-site] branch asf-site updated: Build at Thu Aug 27 16:37:14 PDT 2020

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch asf-site in repository https://gitbox.apache.org/repos/asf/incubator-tvm-site.git The following commit(s) were added to refs/heads/asf-site by this push: new 5c3e530 Build at Thu Aug 27 16:

[incubator-tvm-site] branch master updated: change

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm-site.git The following commit(s) were added to refs/heads/master by this push: new 42186fc change 42186fc is described

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

icemelon9 commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478733360 ## File path: include/tvm/runtime/vm/bytecode.h ## @@ -204,6 +207,13 @@ struct Instruction { RegName tensor; RegName newshape;

[incubator-tvm] branch master updated (30cd230 -> 1899ad8)

This is an automated email from the ASF dual-hosted git repository. lmzheng pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 30cd230 [BYOC][ETHOSN] Add support for quantized convolution (#6335) add 1899ad8 [Ansor][AutoTVM v2.0]

[GitHub] [incubator-tvm] mbrookhart commented on pull request #6351: Dynamic ONNX Importer

mbrookhart commented on pull request #6351: URL: https://github.com/apache/incubator-tvm/pull/6351#issuecomment-682212270 cc @zhiics @icemelon9 This is an automated message from the Apache Git Service. To respond to the mess

[GitHub] [incubator-tvm] hypercubestart commented on a change in pull request #5812: Bring Your Own Datatypes

hypercubestart commented on a change in pull request #5812: URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r478711025 ## File path: python/tvm/relay/frontend/change_datatype.py ## @@ -0,0 +1,88 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] mbrookhart opened a new pull request #6351: Dynamic ONNX Importer

mbrookhart opened a new pull request #6351: URL: https://github.com/apache/incubator-tvm/pull/6351 Hello Friends, Over the last couple of months, @electriclilies and I have been working to add more dynamic support to relay ops, to separate the dynamic implementations into a dyn name

[GitHub] [incubator-tvm] hypercubestart commented on a change in pull request #5812: Bring Your Own Datatypes

hypercubestart commented on a change in pull request #5812: URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r478613686 ## File path: python/tvm/relay/frontend/change_datatype.py ## @@ -0,0 +1,88 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] jwfromm commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

jwfromm commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478697839 ## File path: python/tvm/relay/transform/memory_alloc.py ## @@ -66,7 +85,7 @@ def is_reshape_only(func): class ManifestAllocPass(ExprMutator): Rev

[GitHub] [incubator-tvm] masahi commented on pull request #6335: [BYOC][ETHOSN] Add support for quantized convolution

masahi commented on pull request #6335: URL: https://github.com/apache/incubator-tvm/pull/6335#issuecomment-682189911 Thanks @mbaret @comaniac This is an automated message from the Apache Git Service. To respond to the messa

[incubator-tvm] branch master updated (e35b7fc -> 30cd230)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from e35b7fc [Relay][Training] Make AutoDiff thread through global function. (#6336) add 30cd230 [BYOC][ETH

[GitHub] [incubator-tvm] masahi merged pull request #6335: [BYOC][ETHOSN] Add support for quantized convolution

masahi merged pull request #6335: URL: https://github.com/apache/incubator-tvm/pull/6335 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 g

[GitHub] [incubator-tvm] junrushao1994 commented on pull request #6347: [Target][Codegen] Use target class in all codegens

junrushao1994 commented on pull request #6347: URL: https://github.com/apache/incubator-tvm/pull/6347#issuecomment-682166368 idk why the CI is retriggered... This is an automated message from the Apache Git Service. To respon

[GitHub] [incubator-tvm] areusch commented on pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#issuecomment-682164848 @zhiics @leandron please take a look when you have a minute and explicitly approve if you're good w/ this change -

[GitHub] [incubator-tvm] areusch commented on a change in pull request #6333: Add docker/lint.sh, for running dockerized lint scripts locally

areusch commented on a change in pull request #6333: URL: https://github.com/apache/incubator-tvm/pull/6333#discussion_r478666133 ## File path: tests/lint/clang_format.sh ## @@ -0,0 +1,23 @@ +#!/bin/bash -e +# Licensed to the Apache Software Foundation (ASF) under one +# or mor

[GitHub] [incubator-tvm] mbrookhart commented on a change in pull request #6337: [RELAY][VM] Enable heterogeneous execution for Relay VM

mbrookhart commented on a change in pull request #6337: URL: https://github.com/apache/incubator-tvm/pull/6337#discussion_r478661229 ## File path: src/relay/analysis/context_analysis.cc ## @@ -0,0 +1,697 @@ +/* + * Licensed to the Apache Software Foundation (ASF) under one + *

[GitHub] [incubator-tvm] jroesch merged pull request #6336: [Relay][Training] Make AutoDiff thread through global function.

jroesch merged pull request #6336: URL: https://github.com/apache/incubator-tvm/pull/6336 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

[incubator-tvm] branch master updated: [Relay][Training] Make AutoDiff thread through global function. (#6336)

This is an automated email from the ASF dual-hosted git repository. jroesch pushed a commit to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git The following commit(s) were added to refs/heads/master by this push: new e35b7fc [Relay][Training] Make AutoDiff

[GitHub] [incubator-tvm] hypercubestart commented on a change in pull request #5812: Bring Your Own Datatypes

hypercubestart commented on a change in pull request #5812: URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r478615669 ## File path: python/tvm/target/datatype.py ## @@ -14,73 +14,153 @@ # KIND, either express or implied. See the License for the # specific

[GitHub] [incubator-tvm] hypercubestart commented on a change in pull request #5812: Bring Your Own Datatypes

hypercubestart commented on a change in pull request #5812: URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r478613686 ## File path: python/tvm/relay/frontend/change_datatype.py ## @@ -0,0 +1,88 @@ +# Licensed to the Apache Software Foundation (ASF) under one

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6335: [BYOC][ETHOSN] Add support for quantized convolution

comaniac commented on a change in pull request #6335: URL: https://github.com/apache/incubator-tvm/pull/6335#discussion_r478610698 ## File path: src/relay/backend/contrib/ethosn/codegen.cc ## @@ -50,6 +50,16 @@ bool IsEthosnOp(const Call& call, const std::string& op_name) {

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

comaniac commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478609685 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY

[GitHub] [incubator-tvm] comaniac commented on pull request #6310: [Ansor][AutoTVM v2.0] Phase 2: Evolutionary Search

comaniac commented on pull request #6310: URL: https://github.com/apache/incubator-tvm/pull/6310#issuecomment-682109549 @merrymercy comment addressed. PTAL. This is an automated message from the Apache Git Service. To respond

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6348: [Ansor][AutoTVM v2.0] Phase 2: Update heavy operations with parallel_for

comaniac commented on a change in pull request #6348: URL: https://github.com/apache/incubator-tvm/pull/6348#discussion_r478604334 ## File path: src/auto_scheduler/search_policy/sketch_policy.cc ## @@ -322,32 +323,40 @@ Array SketchPolicyNode::GenerateSketches() { } Array S

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

leandron commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r478604162 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

leandron commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r478598548 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

comaniac commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r478591988 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

leandron commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r478586988 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6302: [tvmc] command line driver 'compile' (part 2/4)

leandron commented on a change in pull request #6302: URL: https://github.com/apache/incubator-tvm/pull/6302#discussion_r478580880 ## File path: python/tvm/driver/tvmc/compiler.py ## @@ -0,0 +1,407 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more cont

[GitHub] [incubator-tvm] tqchen edited a comment on issue #6332: [VOTE] Apache TVM Graduation

tqchen edited a comment on issue #6332: URL: https://github.com/apache/incubator-tvm/issues/6332#issuecomment-682068380 Thanks everyone who voted, the results are now in https://github.com/apache/incubator-tvm/issues/6350 Th

[GitHub] [incubator-tvm] tqchen edited a comment on issue #6332: [VOTE] Apache TVM Graduation

tqchen edited a comment on issue #6332: URL: https://github.com/apache/incubator-tvm/issues/6332#issuecomment-682068380 Thanks everyone who voted, the results are now in https://lists.apache.org/thread.html/rc8cdb81de0dc0e1f96194afc1b911365ba8fd4b155ccc0914e70cdcd%40%3Cdev.tvm.apache.org%3E

[GitHub] [incubator-tvm] tqchen opened a new issue #6350: [RESULT][VOTE] Apache Graduation

tqchen opened a new issue #6350: URL: https://github.com/apache/incubator-tvm/issues/6350 Thanks everyone who voted. Voting thread: https://lists.apache.org/thread.html/rd5b8eefe49af09a2d0913758a5e5737b3fdb9072bc0becf4a2b2c7ee%40%3Cdev.tvm.apache.org%3E The results are:

[GitHub] [incubator-tvm] tqchen commented on issue #6332: [VOTE] Apache TVM Graduation

tqchen commented on issue #6332: URL: https://github.com/apache/incubator-tvm/issues/6332#issuecomment-682068380 Thanks everyone. The results are: +1 Markus Junru ziheng Thierry Henry Lily Jared Haichen Masa Morita Wuwei Siju Gon Timothy Ch

[GitHub] [incubator-tvm] FrozenGene commented on pull request #5913: [random] support random fill

FrozenGene commented on pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-681915191 Thanks for reminding @merrymercy. My agenda is completely full tomorrow and weekend. I could do this next week. --

[GitHub] [incubator-tvm] merrymercy commented on pull request #5913: [random] support random fill

merrymercy commented on pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-681906084 @FrozenGene Can you send the follow up PRs to enable this in ansor and autotvm? This is an automated

[GitHub] [incubator-tvm] merrymercy edited a comment on pull request #5913: [random] support random fill

merrymercy edited a comment on pull request #5913: URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-681906084 @FrozenGene Can you send the follow-up PRs to enable this in ansor and autotvm? This is an aut

[GitHub] [incubator-tvm] kongroo opened a new pull request #6349: [CODEGEN][CUDA]: fix cuda half math function is undefined: herf

kongroo opened a new pull request #6349: URL: https://github.com/apache/incubator-tvm/pull/6349 I got an "identifier herf undefined" error when converting a model into TVM, which can be reproduced by the following code ``` import torch import numpy as np import tvm from tvm i

[GitHub] [incubator-tvm] jtuyls commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

jtuyls commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478304888 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY i

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

leandron commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478288536 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY

[GitHub] [incubator-tvm] jtuyls commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

jtuyls commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478283171 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY i

[GitHub] [incubator-tvm] jtuyls commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

jtuyls commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478283171 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY i

[GitHub] [incubator-tvm] leandron commented on a change in pull request #6342: [CI][Contrib] Add Vitis-AI docker installation

leandron commented on a change in pull request #6342: URL: https://github.com/apache/incubator-tvm/pull/6342#discussion_r478273962 ## File path: docker/Dockerfile.ci_cpu ## @@ -83,3 +83,7 @@ RUN bash /install/ubuntu_install_caffe.sh # Github Arm(R) Ethos(TM)-N NPU driver COPY

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #6335: [BYOC][ETHOSN] Add support for quantized convolution

mbaret commented on a change in pull request #6335: URL: https://github.com/apache/incubator-tvm/pull/6335#discussion_r478256059 ## File path: src/relay/backend/contrib/ethosn/codegen.cc ## @@ -50,6 +50,16 @@ bool IsEthosnOp(const Call& call, const std::string& op_name) { }

[GitHub] [incubator-tvm] jcf94 opened a new pull request #6348: [Ansor][AutoTVM v2.0] Phase 2: Update heavy operation with parallel_for

jcf94 opened a new pull request #6348: URL: https://github.com/apache/incubator-tvm/pull/6348 For the full upstream plan, see [Ansor RFC](https://discuss.tvm.ai/t/rfc-ansor-an-auto-scheduler-for-tvm-autotvm-v2-0/7005/21). This PR contains some small fix: - Use parallel_for to spee