[GitHub] [tvm-rfcs] manupa-arm commented on pull request #23: [RFC][TIR] Adding annotation field to tir.allocate

manupa-arm commented on pull request #23: URL: https://github.com/apache/tvm-rfcs/pull/23#issuecomment-930796849 @tqchen merge? -- 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-rfcs] manupa-arm commented on pull request #22: [RFC][TIR] TIR Non-scalar Constants

manupa-arm commented on pull request #22: URL: https://github.com/apache/tvm-rfcs/pull/22#issuecomment-930796609 @areusch a friendly ping! -- 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] FrozenGene commented on a change in pull request #9157: [Caffe Frontend] Add support for Permute layer

FrozenGene commented on a change in pull request #9157: URL: https://github.com/apache/tvm/pull/9157#discussion_r719032634 ## File path: tests/python/frontend/caffe/test_forward.py ## @@ -586,6 +586,27 @@ def test_forward_LRN(): _test_lrn(data, local_size=3, alpha=2.0,

[GitHub] [tvm] mshr-h opened a new pull request #9157: [Caffe Frontend] Add support for Permute layer

mshr-h opened a new pull request #9157: URL: https://github.com/apache/tvm/pull/9157 Added Permute layer support. Related to #6206, #9060 @fernchen @zhiics @tqchen @FrozenGene Can you take a look at this PR, please? Thanks! -- This is an automated message from the Apache Git

[GitHub] [tvm] Hzfengsy commented on pull request #9100: [TensorIR][Bugfix] Fallback Mechanism in Fuse for failure of DetectIterMap

Hzfengsy commented on pull request #9100: URL: https://github.com/apache/tvm/pull/9100#issuecomment-930708601 @jinhongyii Can you update the PR then we can merge it -- 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] Hzfengsy commented on a change in pull request #9115: [TVMScript] Script namespace changes

Hzfengsy commented on a change in pull request #9115: URL: https://github.com/apache/tvm/pull/9115#discussion_r719017074 ## File path: tests/python/unittest/test_aot_legalize_packed_call.py ## @@ -70,8 +71,8 @@ def tir_packed_call() -> None: def test_aot_packed_call(): -

[GitHub] [tvm] Hzfengsy commented on a change in pull request #9115: [TVMScript] Script namespace changes

Hzfengsy commented on a change in pull request #9115: URL: https://github.com/apache/tvm/pull/9115#discussion_r719009665 ## File path: tests/python/unittest/test_tvmscript_spans.py ## @@ -18,26 +18,26 @@ import inspect import tvm -import tvm.script -from tvm import tir

[GitHub] [tvm] Hzfengsy commented on a change in pull request #9115: [TVMScript] Script namespace changes

Hzfengsy commented on a change in pull request #9115: URL: https://github.com/apache/tvm/pull/9115#discussion_r719009665 ## File path: tests/python/unittest/test_tvmscript_spans.py ## @@ -18,26 +18,26 @@ import inspect import tvm -import tvm.script -from tvm import tir

[GitHub] [tvm] junrushao1994 commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718998477 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [tvm] junrushao1994 commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718998301 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,341 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718993549 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[tvm] branch main updated (fafd164 -> 677f2d4)

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 fafd164 Update find cublas so it search default path if needed. (#9149) add 677f2d4 [Hotfix][Testing] Wait for

[GitHub] [tvm] junrushao1994 merged pull request #9150: [Hotfix][Testing] Wait for RPCServer to be established

junrushao1994 merged pull request #9150: URL: https://github.com/apache/tvm/pull/9150 -- 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] zxybazh commented on pull request #9156: Fix typo

zxybazh commented on pull request #9156: URL: https://github.com/apache/tvm/pull/9156#issuecomment-930676143 LGTM, thanks for the fix. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718990764 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] comaniac commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

comaniac commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718989355 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718989407 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] junrushao1994 commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718987360 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718985630 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718984772 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718986692 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] junrushao1994 commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718986533 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[tvm] branch main updated (da5b4fb -> fafd164)

This is an automated email from the ASF dual-hosted git repository. mbrookhart pushed a change to branch main in repository https://gitbox.apache.org/repos/asf/tvm.git. from da5b4fb [TIR][LowerMatchBuffer] Fix lowering strides when source region has higher dimension than the buffer

[GitHub] [tvm] mbrookhart commented on pull request #9149: Update find cublas so it searches the default path if needed.

mbrookhart commented on pull request #9149: URL: https://github.com/apache/tvm/pull/9149#issuecomment-930663419 Thanks @rkimball -- 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] mbrookhart merged pull request #9149: Update find cublas so it searches the default path if needed.

mbrookhart merged pull request #9149: URL: https://github.com/apache/tvm/pull/9149 -- 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] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718985914 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718985630 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] shingjan commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

shingjan commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718984772 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] cloudhan closed pull request #9148: Fix building with llvm 13

cloudhan closed pull request #9148: URL: https://github.com/apache/tvm/pull/9148 -- 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] Oreobird opened a new pull request #9156: Fix typo

Oreobird opened a new pull request #9156: URL: https://github.com/apache/tvm/pull/9156 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 from

[GitHub] [tvm] comaniac commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

comaniac commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718954399 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] comaniac commented on pull request #9127: [BYOC] support arbitrary input dims for add/mul/relu of dnnl c_src codegen

comaniac commented on pull request #9127: URL: https://github.com/apache/tvm/pull/9127#issuecomment-929675578 > Can you add a test? Hey @masahi, the DNNL C codegen currently is not enabled in the CI so it won't be tested anyways. The reason we didn't deprecate it is because it is a

[GitHub] [tvm-rfcs] junrushao1994 commented on pull request #37: Introduce the Arm(R) Ethos(TM)-U Cascading Planner

junrushao1994 commented on pull request #37: URL: https://github.com/apache/tvm-rfcs/pull/37#issuecomment-930498144 Thanks for the RFC! - The TE scheduling part (rolling-buffer) looks good to me. - Grouping operators together might be challenging in Relay fusion and lowering, and

[GitHub] [tvm] tmoreau89 commented on pull request #9093: [UnitTests] Enable minimum testing on Vulkan target in CI

tmoreau89 commented on pull request #9093: URL: https://github.com/apache/tvm/pull/9093#issuecomment-929640077 Thank you @Lunderberg @csullivan we finally have Vulkan CI! -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] kparzysz-quic edited a comment on pull request #9138: [LLVM] Make changes needed for opaque pointers

kparzysz-quic edited a comment on pull request #9138: URL: https://github.com/apache/tvm/pull/9138#issuecomment-930279683 LLVM IR is eliminating types in pointers, so there will only be `ptr` for a pointer type (i.e. pointers will be "opaque"), instead of `i32*` or `float*`. This will

[GitHub] [tvm] kparzysz-quic commented on pull request #9138: [LLVM] Make changes needed for opaque pointers

kparzysz-quic commented on pull request #9138: URL: https://github.com/apache/tvm/pull/9138#issuecomment-930279683 -- 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] jroesch merged pull request #8849: [5/6] Arm(R) Ethos(TM)-U NPU codegen integration

jroesch merged pull request #8849: URL: https://github.com/apache/tvm/pull/8849 -- 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 merged pull request #9137: [QNN] Add nn.global_avgpool to FQ2i

masahi merged pull request #9137: URL: https://github.com/apache/tvm/pull/9137 -- 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 change in pull request #9108: [Runtime] Pipeline Executor Second patch, configuration load and executor export/import.

huajsj commented on a change in pull request #9108: URL: https://github.com/apache/tvm/pull/9108#discussion_r718010902 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -501,17 +537,18 @@ class PipelineExecutorFactoryModule(object): """ -def

[GitHub] [tvm] electriclilies commented on issue #9057: [VOTE] Adopt round-robin assignment of reviewers for GitHub pull request reviewer assignment.

electriclilies commented on issue #9057: URL: https://github.com/apache/tvm/issues/9057#issuecomment-930626090 Thanks @manupa-arm @Mousius and @leandron for bringing these points up. 
Building off what you said, I just wanted to point out that I think that this vote is really two

[GitHub] [tvm] junrushao1994 commented on a change in pull request #9111: [Meta Schedule][M3b] Runner

junrushao1994 commented on a change in pull request #9111: URL: https://github.com/apache/tvm/pull/9111#discussion_r717973421 ## File path: python/tvm/meta_schedule/runner/config.py ## @@ -0,0 +1,189 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] zxybazh commented on pull request #9150: [Hotfix][Testing] Wait for RPCServer to be established

zxybazh commented on pull request #9150: URL: https://github.com/apache/tvm/pull/9150#issuecomment-930449470 LGTM. Thanks for the fix. -- 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] jiangjiajun edited a comment on pull request #9126: [Frontend][PaddlePaddle][Part1] Add 100+ operators for PaddlePaddle

jiangjiajun edited a comment on pull request #9126: URL: https://github.com/apache/tvm/pull/9126#issuecomment-930119644 -- 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-rfcs] junrushao1994 commented on pull request #36: [RFC][TVMScript] New namespace for tvmscript

junrushao1994 commented on pull request #36: URL: https://github.com/apache/tvm-rfcs/pull/36#issuecomment-930344604 Thanks guys for the discussion! The RFC is merged :-) -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] jroesch commented on a change in pull request #8849: [5/6] Arm(R) Ethos(TM)-U NPU codegen integration

jroesch commented on a change in pull request #8849: URL: https://github.com/apache/tvm/pull/8849#discussion_r718042008 ## File path: python/tvm/relay/backend/contrib/ethosu/codegen.py ## @@ -0,0 +1,83 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] tqchen commented on issue #8629: Link librvm_runtime.so get Error.

tqchen commented on issue #8629: URL: https://github.com/apache/tvm/issues/8629#issuecomment-930554230 please check if the problem still exists in the latest main, based on my reading it should be fixed by the TVM_DLL prefix -- This is an automated message from the Apache Git Service.

[GitHub] [tvm] Mousius commented on pull request #9128: [CI] Split Integration tests out of first phase of pipeline

Mousius commented on pull request #9128: URL: https://github.com/apache/tvm/pull/9128#issuecomment-929966726 Had to re-push due to a flakey unit test on the PR build, docker-staging build is here now:

[GitHub] [tvm] AndrewZhaoLuo commented on a change in pull request #9126: [Frontend][PaddlePaddle][Part1] Add 100+ operators for PaddlePaddle

AndrewZhaoLuo commented on a change in pull request #9126: URL: https://github.com/apache/tvm/pull/9126#discussion_r718024142 ## File path: tests/python/frontend/paddlepaddle/test_forward.py ## @@ -607,55 +960,53 @@ def slice4(inputs): x1 = paddle.to_tensor([3]) +

[GitHub] [tvm] junrushao1994 merged pull request #9132: [Meta Schedule][M3a] SearchStrategy

junrushao1994 merged pull request #9132: URL: https://github.com/apache/tvm/pull/9132 -- 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] jiangjiajun commented on pull request #9124: add PaddlePaddle tutorial

jiangjiajun commented on pull request #9124: URL: https://github.com/apache/tvm/pull/9124#issuecomment-930127471 Hi @junrushao1994 Could you review this pull request, since paddle frontend is available, this tutorial will be useful for PaddlePaddle users -- This is an automated message

[GitHub] [tvm] Hzfengsy commented on pull request #9121: [TIR] add loop partition hint pragma

Hzfengsy commented on pull request #9121: URL: https://github.com/apache/tvm/pull/9121#issuecomment-929971822 Thanks, @wrongtest -- 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] masahi merged pull request #9133: [Frontend][PyTorch] support for quantized conv_transpose2d op

masahi merged pull request #9133: URL: https://github.com/apache/tvm/pull/9133 -- 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] tqchen closed issue #8629: Link librvm_runtime.so get Error.

tqchen closed issue #8629: URL: https://github.com/apache/tvm/issues/8629 -- 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-rfcs] junrushao1994 merged pull request #36: [RFC][TVMScript] New namespace for tvmscript

junrushao1994 merged pull request #36: URL: https://github.com/apache/tvm-rfcs/pull/36 -- 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] junrushao1994 commented on a change in pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on a change in pull request #9153: URL: https://github.com/apache/tvm/pull/9153#discussion_r718930001 ## File path: python/tvm/meta_schedule/runner/local_runner.py ## @@ -0,0 +1,367 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or

[GitHub] [tvm] jroesch commented on pull request #9128: [CI] Split Integration tests out of first phase of pipeline

jroesch commented on pull request #9128: URL: https://github.com/apache/tvm/pull/9128#issuecomment-929698447 -- 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-rfcs] electriclilies commented on pull request #29: Migrating Target Attributes to IRModule

electriclilies commented on pull request #29: URL: https://github.com/apache/tvm-rfcs/pull/29#issuecomment-930403179 Overall this seems like a good change! One question I have is what the relationship between PassContext and the IRModule attributes will be in the future. I think that

[GitHub] [tvm] tqchen commented on pull request #9150: [Hotfix][Testing] Wait for RPCServer to be established

tqchen commented on pull request #9150: URL: https://github.com/apache/tvm/pull/9150#issuecomment-930498047 -- 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] masahi merged pull request #9144: [OpenCL] Remove redundant visit statement in CodeGen.

masahi merged pull request #9144: URL: https://github.com/apache/tvm/pull/9144 -- 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] cloudhan commented on pull request #9148: Fix building with llvm 13

cloudhan commented on pull request #9148: URL: https://github.com/apache/tvm/pull/9148#issuecomment-930084619 @junrushao1994 Please take a quick look at this simple change. -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[GitHub] [tvm] electriclilies commented on pull request #9134: [Relay] Add LowerTEPass into vm lowering proecss

electriclilies commented on pull request #9134: URL: https://github.com/apache/tvm/pull/9134#issuecomment-930439403 Just catching up after being out for a week -- is "vm_mod" used for anything other than name mangling? Also is LowerTEPass supposed replacing any existing lowering logic

[GitHub] [tvm] mbs-octoml edited a comment on pull request #9038: [Relay] Merge analysis/context_analysis.cc and transforms/device_annotation.cc

mbs-octoml edited a comment on pull request #9038: URL: https://github.com/apache/tvm/pull/9038#issuecomment-929644148 @areusch, @jroesch thank you and PTAL: - Rebased on main - All unit tests (plus a new one for match :-) in script form - Split out device domains and

[GitHub] [tvm] zxybazh commented on pull request #9132: [Meta Schedule][M3a] SearchStrategy

zxybazh commented on pull request #9132: URL: https://github.com/apache/tvm/pull/9132#issuecomment-929838443 Let's get it merged if there are no further issues. -- 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] leandron merged pull request #9141: [CI] Fix Google Mock differences between Ubuntu 18.04 and 16.04

leandron merged pull request #9141: URL: https://github.com/apache/tvm/pull/9141 -- 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 merged pull request #9146: [ONNX] Fix unsqueeze constant expr

masahi merged pull request #9146: URL: https://github.com/apache/tvm/pull/9146 -- 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] mikepapadim commented on pull request #9031: [CI] Prevent the complete Jenkins pipeline to run when files commited only to `/docs`

mikepapadim commented on pull request #9031: URL: https://github.com/apache/tvm/pull/9031#issuecomment-930297038 PTAL -- 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] masahi merged pull request #9127: [BYOC] support arbitrary input dims for add/mul/relu of dnnl c_src codegen

masahi merged pull request #9127: URL: https://github.com/apache/tvm/pull/9127 -- 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] tmoreau89 merged pull request #9093: [UnitTests] Enable minimum testing on Vulkan target in CI

tmoreau89 merged pull request #9093: URL: https://github.com/apache/tvm/pull/9093 -- 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] junrushao1994 commented on pull request #9150: [Hotfix][Testing] Wait for RPCServer to be established

junrushao1994 commented on pull request #9150: URL: https://github.com/apache/tvm/pull/9150#issuecomment-930448462 -- 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] masahi commented on a change in pull request #9108: [Runtime] Pipeline Executor Second patch, configuration load and executor export/import.

masahi commented on a change in pull request #9108: URL: https://github.com/apache/tvm/pull/9108#discussion_r717965514 ## File path: python/tvm/contrib/pipeline_executor.py ## @@ -86,8 +87,43 @@ class PipelineModule(object): Common interface for pipeline executor

[GitHub] [tvm] Lunderberg commented on pull request #9151: [UnitTests] Parametrized test_mod_export, marked failing portions with xfail

Lunderberg commented on pull request #9151: URL: https://github.com/apache/tvm/pull/9151#issuecomment-930446958 @mbs-octoml -- 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] masahi commented on a change in pull request #9146: [ONNX] Fix unsqueeze constant expr

masahi commented on a change in pull request #9146: URL: https://github.com/apache/tvm/pull/9146#discussion_r718055932 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -1468,18 +1468,26 @@ class Unsqueeze(OnnxOpConverter): """Operator converter for Unsqueeze."""

[GitHub] [tvm] shingjan commented on pull request #9153: [Meta Schedule][M3a]Local runner

shingjan commented on pull request #9153: URL: https://github.com/apache/tvm/pull/9153#issuecomment-930575270 One `RPCRunner` test is failing and I will rebase after the fix (#9150) gets in. -- This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [tvm] jiangjiajun commented on a change in pull request #9126: [Frontend][PaddlePaddle][Part1] Add 100+ operators for PaddlePaddle

jiangjiajun commented on a change in pull request #9126: URL: https://github.com/apache/tvm/pull/9126#discussion_r718439340 ## File path: tests/python/frontend/paddlepaddle/test_forward.py ## @@ -607,55 +960,53 @@ def slice4(inputs): x1 = paddle.to_tensor([3]) +

[GitHub] [tvm] vinx13 merged pull request #9145: [TIR][LowerMatchBuffer] Fix lowering strides when source region has higher dimension than the buffer

vinx13 merged pull request #9145: URL: https://github.com/apache/tvm/pull/9145 -- 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] jroesch commented on pull request #9038: [Relay] Merge analysis/context_analysis.cc and transforms/device_annotation.cc

jroesch commented on pull request #9038: URL: https://github.com/apache/tvm/pull/9038#issuecomment-930361272 I am going to land this, if people have follow-ups we can do them in the final PR which actually turns this on. -- This is an automated message from the Apache Git Service. To

[GitHub] [tvm] jroesch commented on pull request #9129: [CI] Pass failFast flag to Jenkins parallel

jroesch commented on pull request #9129: URL: https://github.com/apache/tvm/pull/9129#issuecomment-929692080 @areusch I feel like this is a great forcing function to fix people's local setup, CI should not be people's personal testing environment (even if some people use it that way). If

[GitHub] [tvm] AndrewZhaoLuo commented on pull request #9146: [ONNX] Fix unsqueeze constant expr

AndrewZhaoLuo commented on pull request #9146: URL: https://github.com/apache/tvm/pull/9146#issuecomment-929701367 @masahi -- 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] masahi commented on pull request #9146: [ONNX] Fix unsqueeze constant expr

masahi commented on pull request #9146: URL: https://github.com/apache/tvm/pull/9146#issuecomment-929720375 @AndrewZhaoLuo Can we also replace `If` below with `op.where(...)`?

[GitHub] [tvm] masahi merged pull request #9139: [Relay][ConvertLayout] Support for qnn.conv2d_transpose

masahi merged pull request #9139: URL: https://github.com/apache/tvm/pull/9139 -- 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-rfcs] tqchen commented on pull request #18: [RFC] Adding initial SVE implementation

tqchen commented on pull request #18: URL: https://github.com/apache/tvm-rfcs/pull/18#issuecomment-930488098 Thanks @sjoerdmeijer , sorry for getting back to this late. If LLVM also encodes the SVE vector as a special type(and not tying the n) it could be a precedence that we can learn

[GitHub] [tvm] mbs-octoml commented on pull request #9038: [Relay] Merge analysis/context_analysis.cc and transforms/device_annotation.cc

mbs-octoml commented on pull request #9038: URL: https://github.com/apache/tvm/pull/9038#issuecomment-929644148 @areusch, @jroesch thank you and PTAL: - Rebased on main - All unit tests (plus a new one for match :-) in script form - Split out devices domains and device-aware

[GitHub] [tvm-rfcs] manupa-arm commented on a change in pull request #22: [RFC][TIR] TIR Non-scalar Constants

manupa-arm commented on a change in pull request #22: URL: https://github.com/apache/tvm-rfcs/pull/22#discussion_r718769206 ## File path: rfcs/0022-tir-non-scalar-constants.md ## @@ -0,0 +1,148 @@ + +- Feature Name: tir_non_scalar_constants +- Start Date: 2021-06-01 +- RFC PR:

[GitHub] [tvm] masahi commented on pull request #9127: [BYOC] support arbitrary input dims for add/mul/relu of dnnl c_src codegen

masahi commented on pull request #9127: URL: https://github.com/apache/tvm/pull/9127#issuecomment-929652322 Can you add a test? -- 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] Hzfengsy merged pull request #9121: [TIR] add loop partition hint pragma

Hzfengsy merged pull request #9121: URL: https://github.com/apache/tvm/pull/9121 -- 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] junrushao1994 merged pull request #9111: [Meta Schedule][M3b] Runner

junrushao1994 merged pull request #9111: URL: https://github.com/apache/tvm/pull/9111 -- 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] sergey-grovety commented on a change in pull request #9092: Issue8717 x86 dws conv2d schedule

sergey-grovety commented on a change in pull request #9092: URL: https://github.com/apache/tvm/pull/9092#discussion_r718423680 ## File path: tests/micro/zephyr/test_zephyr_armv7m.py ## @@ -0,0 +1,267 @@ +# Licensed to the Apache Software Foundation (ASF) under one +# or more

[GitHub] [tvm] junrushao1994 commented on pull request #9153: [Meta Schedule][M4a] Local runner

junrushao1994 commented on pull request #9153: URL: https://github.com/apache/tvm/pull/9153#issuecomment-930596901 Thanks @shingjan for the PR. It's overall in good shape, and I left only one comment on potential duplication -- This is an automated message from the Apache Git Service.

[GitHub] [tvm] Lunderberg commented on pull request #9091: [TIR] tir.transform.StorageFlatten refactor

Lunderberg commented on pull request #9091: URL: https://github.com/apache/tvm/pull/9091#issuecomment-930294838 Latest round of changes, added another pass to remove assert statements that can be statically validated. These are placed by ArgBinder::Bind if it can't verify a constraint at

[GitHub] [tvm] masahi commented on pull request #9152: Pytorch qnn frontend. Avoid explicit pad in case of 'zero_point == 0'

masahi commented on pull request #9152: URL: https://github.com/apache/tvm/pull/9152#issuecomment-930603972 Explicit pad is necessary for BYOC use cases where we don't use QNN lowering. So the pad value needs to be available at a QNN graph level. -- This is an automated message from

[GitHub] [tvm] jroesch merged pull request #9128: [CI] Split Integration tests out of first phase of pipeline

jroesch merged pull request #9128: URL: https://github.com/apache/tvm/pull/9128 -- 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] jroesch commented on pull request #9138: [LLVM] Make changes needed for opaque pointers

jroesch commented on pull request #9138: URL: https://github.com/apache/tvm/pull/9138#issuecomment-929898316 -- 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] wrongtest commented on pull request #9121: [TIR] add loop partition hint pragma

wrongtest commented on pull request #9121: URL: https://github.com/apache/tvm/pull/9121#issuecomment-929903485 @Hzfengsy hi~ I resolve the comment issues，can you kindly take another round of review：）？ -- This is an automated message from the Apache Git Service. To respond to the

[GitHub] [tvm] jroesch merged pull request #9138: [LLVM] Make changes needed for opaque pointers

jroesch merged pull request #9138: URL: https://github.com/apache/tvm/pull/9138 -- 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] jiangjiajun commented on pull request #9126: [Frontend][PaddlePaddle][Part1] Add 100+ operators for PaddlePaddle

jiangjiajun commented on pull request #9126: URL: https://github.com/apache/tvm/pull/9126#issuecomment-930119644 > This PR is still too big I think considering most work here is unrelated to each other. Can you remove operators from this PR until you are down to ~+300 loc? > > Just

[GitHub] [tvm] junrushao1994 commented on pull request #9115: [TVMScript] Script namespace changes

junrushao1994 commented on pull request #9115: URL: https://github.com/apache/tvm/pull/9115#issuecomment-930539788 Thanks @Hzfengsy for the hard work, greatly improving the TVMScript syntax! Let's move quickly, address comments and get this PR merged :-) -- This is an automated message

[GitHub] [tvm] masahi edited a comment on pull request #9146: [ONNX] Fix unsqueeze constant expr

masahi edited a comment on pull request #9146: URL: https://github.com/apache/tvm/pull/9146#issuecomment-929720375 @AndrewZhaoLuo Can we also replace `If` below with `op.where(...)`? To avoid making VM a requirement.

[GitHub] [tvm] gromero commented on pull request #9090: [microTVM] Add wrapper for creating project using a MLF

gromero commented on pull request #9090: URL: https://github.com/apache/tvm/pull/9090#issuecomment-930236057 @areusch @Mousius Thanks for the reviews. Sorry for the respin delay. I've fixed the offending line to satisfy the linter and also fixed the type hints for the added function

[GitHub] [tvm] electriclilies edited a comment on issue #9057: [VOTE] Adopt round-robin assignment of reviewers for GitHub pull request reviewer assignment.

electriclilies edited a comment on issue #9057: URL: https://github.com/apache/tvm/issues/9057#issuecomment-930626090 -- 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] masahi merged pull request #9143: [UnitTest] Parametrized test_conv2d_int8_intrinsics

masahi merged pull request #9143: URL: https://github.com/apache/tvm/pull/9143 -- 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   3   >