[GitHub] [incubator-tvm] zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398772992 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@ -678,6

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398810119 ## File path: src/relay/qnn/op/mul.cc ## @@ -71,31 +59,35 @@ Expr QnnMulCanonicalize(const Attrs& attrs,

[GitHub] [incubator-tvm] maheshambule commented on issue #5052: Relay to ONNX converter

maheshambule commented on issue #5052: Relay to ONNX converter URL: https://github.com/apache/incubator-tvm/pull/5052#issuecomment-604637351 RFC created at https://discuss.tvm.ai/t/rfc-relay-to-onnx/6101 This is an automated

[GitHub] [incubator-tvm] tqchen commented on issue #5152: ONNX Compatibility

tqchen commented on issue #5152: ONNX Compatibility URL: https://github.com/apache/incubator-tvm/issues/5152#issuecomment-604514502 Thanks for asking the question, please open a new thread on https://discuss.tvm.ai/ This is

[GitHub] [incubator-tvm] tqchen closed issue #5152: ONNX Compatibility

tqchen closed issue #5152: ONNX Compatibility URL: https://github.com/apache/incubator-tvm/issues/5152 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the

[GitHub] [incubator-tvm] FrozenGene commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added

FrozenGene commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-604521317 @siju-samuel please rebase so that i can handle it.

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398786009 ## File path: src/relay/qnn/op/mul.cc ## @@ -71,31 +59,35 @@ Expr QnnMulCanonicalize(const Attrs&

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398787686 ## File path: src/relay/qnn/op/add.cc ## @@ -97,39 +66,29 @@ Expr QnnAddCanonicalize(const Attrs&

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398780962 ## File path: python/tvm/relay/qnn/op/qnn.py ## @@ -436,3 +436,54 @@ def mul(lhs, rhs, lhs_scale,

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398784846 ## File path: src/relay/qnn/op/mul.cc ## @@ -42,22 +42,10 @@ namespace qnn { Expr

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398788973 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,155 @@ #include #include #include

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398806276 ## File path: src/relay/qnn/op/add.cc ## @@ -97,39 +66,29 @@ Expr QnnAddCanonicalize(const Attrs& attrs,

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398760547 ## File path: src/relay/transforms/partition_graph.cc ## @@ -365,35 +374,113

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398810119 ## File path: src/relay/qnn/op/mul.cc ## @@ -71,31 +59,35 @@ Expr QnnMulCanonicalize(const Attrs& attrs,

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398810414 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,155 @@ #include #include #include

[GitHub] [incubator-tvm] shoubhik commented on issue #5153: Adding support for QNN subtract op

shoubhik commented on issue #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#issuecomment-604550015 @anijain2305 can you take a look at this PR. This is an automated message

[GitHub] [incubator-tvm] shoubhik opened a new pull request #5153: Adding support for QNN subtract op

shoubhik opened a new pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153 * Adding support for QNN subtract operator. * Refactoring the code for QNN Binary operators to use a common infrastructure. Thanks for

[GitHub] [incubator-tvm] zhiics commented on issue #5106: [Relay][MergeComposite] Support TupleGetItem in body of pattern

zhiics commented on issue #5106: [Relay][MergeComposite] Support TupleGetItem in body of pattern URL: https://github.com/apache/incubator-tvm/pull/5106#issuecomment-604573130 @trevor-m Can you retrigger the CI? This is an

[GitHub] [incubator-tvm] ANSHUMAN87 commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

ANSHUMAN87 commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604639849 @tqchen, @masahi: Thanks for your feedback. However I couldn't not agree completely on the reasonings shared by masahi.

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398816558 ## File path: src/relay/qnn/op/mul.cc ## @@ -42,22 +42,10 @@ namespace qnn { Expr

[incubator-tvm] branch master updated (b5ec071 -> fdb7164)

This is an automated email from the ASF dual-hosted git repository. tqchen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from b5ec071 [RELAY] Added a AnnotatedRegion utility class (#5030) add fdb7164 [Doc] TVM release process

[GitHub] [incubator-tvm] tqchen merged pull request #5151: [Doc] TVM release process

tqchen merged pull request #5151: [Doc] TVM release process URL: https://github.com/apache/incubator-tvm/pull/5151 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398747412 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@ -678,6

[incubator-tvm] branch master updated (fdb7164 -> 35ee8f6)

This is an automated email from the ASF dual-hosted git repository. haichen pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from fdb7164 [Doc] TVM release process (#5151) add 35ee8f6 [Relay][OP] Register topi schedule for Relay

[GitHub] [incubator-tvm] icemelon9 merged pull request #5131: [Relay][OP] Register topi schedule for Relay fast_exp and fast_tanh

icemelon9 merged pull request #5131: [Relay][OP] Register topi schedule for Relay fast_exp and fast_tanh URL: https://github.com/apache/incubator-tvm/pull/5131 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] icemelon9 commented on issue #5131: [Relay][OP] Register topi schedule for Relay fast_exp and fast_tanh

icemelon9 commented on issue #5131: [Relay][OP] Register topi schedule for Relay fast_exp and fast_tanh URL: https://github.com/apache/incubator-tvm/pull/5131#issuecomment-604568222 Thanks @selo1412 @comaniac. This is now merged.

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398768598 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@ -678,6

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

comaniac commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398768598 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@ -678,6

[GitHub] [incubator-tvm] tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

tqchen commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-604516628 OK, however, note that havinbg a arena based allocator will likely mean remove the vmalloc based versions(for simplicity

[GitHub] [incubator-tvm] tqchen edited a comment on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

tqchen edited a comment on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-604516628 OK, however, note that havinbg a arena based allocator will likely mean remove the vmalloc based versions(for

[GitHub] [incubator-tvm] tqchen commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

tqchen commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604546479 I agree that given the current support of chainer, perhaps we should not introduce this frontend.

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

zhiics commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398761325 ## File path: src/relay/transforms/partition_graph.cc ## @@ -364,36 +388,114

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #5153: Adding support for QNN subtract op

zhiics commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398855417 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,151 @@ #include #include #include

[GitHub] [incubator-tvm] yongwww commented on issue #4312: [TOPI][Relay][OP] Dynamic NMS and strided_slice

yongwww commented on issue #4312: [TOPI][Relay][OP] Dynamic NMS and strided_slice URL: https://github.com/apache/incubator-tvm/pull/4312#issuecomment-604670227 @tqchen I am working on this pr now, will update it soon This is

[GitHub] [incubator-tvm] tmoreau89 commented on issue #5102: [VOTE] VTA HW/SW refactor

tmoreau89 commented on issue #5102: [VOTE] VTA HW/SW refactor URL: https://github.com/apache/incubator-tvm/issues/5102#issuecomment-604683379 Thanks for everyone that voted closing the vote now. This is an automated message

[GitHub] [incubator-tvm] tmoreau89 closed issue #5102: [VOTE] VTA HW/SW refactor

tmoreau89 closed issue #5102: [VOTE] VTA HW/SW refactor URL: https://github.com/apache/incubator-tvm/issues/5102 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398850100 ## File path: src/relay/qnn/op/mul.cc ## @@ -71,31 +59,35 @@ Expr QnnMulCanonicalize(const Attrs& attrs,

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398849702 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,151 @@ #include #include #include

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398849174 ## File path: src/relay/qnn/op/add.cc ## @@ -97,39 +66,29 @@ Expr QnnAddCanonicalize(const Attrs&

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398849174 ## File path: src/relay/qnn/op/add.cc ## @@ -97,39 +66,29 @@ Expr QnnAddCanonicalize(const Attrs&

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398857826 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,151 @@ #include #include #include

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398857587 ## File path: src/relay/qnn/op/add.cc ## @@ -97,39 +66,29 @@ Expr QnnAddCanonicalize(const Attrs& attrs,

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398847589 ## File path: src/relay/qnn/op/mul.cc ## @@ -71,31 +59,35 @@ Expr QnnMulCanonicalize(const Attrs&

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op

anijain2305 commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398847759 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,155 @@ #include #include #include

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398851124 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,151 @@ #include #include #include

[GitHub] [incubator-tvm] shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op

shoubhik commented on a change in pull request #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#discussion_r398862289 ## File path: src/relay/qnn/op/op_common.h ## @@ -30,14 +30,151 @@ #include #include #include

[GitHub] [incubator-tvm] masahi commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

masahi commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604681188 See https://discuss.tvm.ai/t/discuss-adding-a-pytorch-frontend/5026 for a RFC on adding the PyTorch backend. Yes, discussion

[GitHub] [incubator-tvm] tmoreau89 commented on issue #5102: [VOTE] VTA HW/SW refactor

tmoreau89 commented on issue #5102: [VOTE] VTA HW/SW refactor URL: https://github.com/apache/incubator-tvm/issues/5102#issuecomment-604688139 I'm glad to announce the results of the vote on VTA HW/SW refactor. This vote passes with 11 +1 votes, no 0 votes, and 0 -1 vote. +1

[GitHub] [incubator-tvm] ANSHUMAN87 edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

ANSHUMAN87 edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604639849 @tqchen, @masahi: Thanks for your feedback. However I couldn't not agree completely on the reasonings shared by

[GitHub] [incubator-tvm] anijain2305 commented on issue #5153: Adding support for QNN subtract op

anijain2305 commented on issue #5153: Adding support for QNN subtract op URL: https://github.com/apache/incubator-tvm/pull/5153#issuecomment-604650530 @zhiics Please take a look as well. This is an automated message from the

[GitHub] [incubator-tvm] masahi edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

masahi edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604681188 See https://discuss.tvm.ai/t/discuss-adding-a-pytorch-frontend/5026 for a RFC on adding the PyTorch frontend.

[GitHub] [incubator-tvm] liangfu commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-604756269 That make sense, since we can have strategies for both runtime and workspace memories.

[GitHub] [incubator-tvm] MarisaKirisame commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

MarisaKirisame commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604819014 Sorry, didnt see that. This is an

[GitHub] [incubator-tvm] tqchen opened a new pull request #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

tqchen opened a new pull request #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154 This PR introduces a new way to handle structural equality for both TIR and relay nodes in an extensive way. - Each object

[GitHub] [incubator-tvm] tqchen edited a comment on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

tqchen edited a comment on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604783300 cc @jroesch @MarisaKirisame @zhiics @wweic @yzhliu @Hzfengsy @merrymercy @junrushao1994

[GitHub] [incubator-tvm] MarisaKirisame commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

MarisaKirisame commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604806944 One trick I had done for alphaequal is, there is an addition flag - must_equal_true, which is default to

[GitHub] [incubator-tvm] tmoreau89 commented on issue #5147: [RUNTIME]crt error handling

tmoreau89 commented on issue #5147: [RUNTIME]crt error handling URL: https://github.com/apache/incubator-tvm/pull/5147#issuecomment-604738799 Thanks @siju-samuel for the changes This is an automated message from the Apache

[GitHub] [incubator-tvm] tmoreau89 merged pull request #5147: [RUNTIME]crt error handling

tmoreau89 merged pull request #5147: [RUNTIME]crt error handling URL: https://github.com/apache/incubator-tvm/pull/5147 This is an automated message from the Apache Git Service. To respond to the message, please log on to

[incubator-tvm] branch master updated (35ee8f6 -> 63937a0)

This is an automated email from the ASF dual-hosted git repository. moreau pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 35ee8f6 [Relay][OP] Register topi schedule for Relay fast_exp and fast_tanh (#5131) add 63937a0

[GitHub] [incubator-tvm] trevor-m commented on issue #5134: [RELAY] Add MergeCompilerRegions pass

trevor-m commented on issue #5134: [RELAY] Add MergeCompilerRegions pass URL: https://github.com/apache/incubator-tvm/pull/5134#issuecomment-604752323 Hello, I am trying to use this (in combination with ) but I am getting a segfault every time I call `MergeCompilerRegions`. Here is a small

[GitHub] [incubator-tvm] trevor-m edited a comment on issue #5134: [RELAY] Add MergeCompilerRegions pass

trevor-m edited a comment on issue #5134: [RELAY] Add MergeCompilerRegions pass URL: https://github.com/apache/incubator-tvm/pull/5134#issuecomment-604752323 Hello, I am trying to use this (in combination with https://github.com/apache/incubator-tvm/pull/5143) but I am getting a segfault

[GitHub] [incubator-tvm] tqchen edited a comment on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

tqchen edited a comment on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604783300 cc @jroesch @MarisaKirisame @zhiics @wweic @yzhliu @Hzfengsy @merrymercy

[GitHub] [incubator-tvm] tmoreau89 commented on issue #5147: [RUNTIME]crt error handling

tmoreau89 commented on issue #5147: [RUNTIME]crt error handling URL: https://github.com/apache/incubator-tvm/pull/5147#issuecomment-604746856 Thanks @liangfu @siju-samuel the PR has been merged. This is an automated message

[GitHub] [incubator-tvm] tqchen commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

tqchen commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604816448 @MarisaKirisame what you asked is supported by the assert_mode_ flag

[GitHub] [incubator-tvm] comaniac commented on issue #5134: [RELAY] Add MergeCompilerRegions pass

comaniac commented on issue #5134: [RELAY] Add MergeCompilerRegions pass URL: https://github.com/apache/incubator-tvm/pull/5134#issuecomment-604754618 @mbaret could you reproduce the failure and try to resolve it? It crashed before partition graph so it should not be the issue of multiple

[GitHub] [incubator-tvm] FrozenGene commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

FrozenGene commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604794706 I agree some points of @ANSHUMAN87 . TVM is so attractive, I think one reason is we are very open and happy to provide

[GitHub] [incubator-tvm] tqchen commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR.

tqchen commented on issue #5154: [NODE][IR] Introduce StructuralEqual Infra for the unified IR. URL: https://github.com/apache/incubator-tvm/pull/5154#issuecomment-604783300 cc @jroesch @MarisaKirisame @zhiics @wweic @yzhliu @Hzfengsy

[GitHub] [incubator-tvm] tqchen commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

tqchen commented on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604663268 @ANSHUMAN87 feel free to send an RFC to the discuss forum to get more feedbacks

[GitHub] [incubator-tvm] masahi edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced

masahi edited a comment on issue #5149: [WIP][Relay][Frontend] Chainer frontend introduced URL: https://github.com/apache/incubator-tvm/pull/5149#issuecomment-604681188 See https://discuss.tvm.ai/t/discuss-adding-a-pytorch-frontend/5026 for a RFC on adding the PyTorch frontend.

[incubator-tvm] branch master updated: [RELAY] Added a AnnotatedRegion utility class (#5030)

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 b5ec071 [RELAY] Added a AnnotatedRegion

[GitHub] [incubator-tvm] zhiics merged pull request #5030: [RELAY] Added a AnnotatedRegion utility class

zhiics merged pull request #5030: [RELAY] Added a AnnotatedRegion utility class URL: https://github.com/apache/incubator-tvm/pull/5030 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] FrozenGene commented on issue #5042: [TF][Relay] TensorFlow Frontend support with shared params

FrozenGene commented on issue #5042: [TF][Relay] TensorFlow Frontend support with shared params URL: https://github.com/apache/incubator-tvm/pull/5042#issuecomment-604309360 ping @srkreddy1238 This is an automated message

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#discussion_r398427277 ## File path: src/runtime/crt/graph_runtime.c ## @@ -208,20 +218,24 @@ int

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#discussion_r398378354 ## File path: src/runtime/crt/crt_runtime_api.c ## @@ -79,7 +79,7 @@ int

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#discussion_r398426202 ## File path: apps/bundle_deploy/Makefile ## @@ -37,6 +37,9 @@ demo:

[GitHub] [incubator-tvm] wrongtest commented on issue #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime

wrongtest commented on issue #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime URL: https://github.com/apache/incubator-tvm/pull/4459#issuecomment-604354652 One possible approach is pack TVM runtime deps thus we do not need to link libtvm.so at runtime. Refer to

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398522928 ## File path: src/relay/transforms/partition_graph.cc ## @@ -165,101

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398523020 ## File path: src/relay/transforms/partition_graph.cc ## @@ -364,36

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398522710 ## File path: src/relay/transforms/partition_graph.cc ## @@ -102,61

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on a change in pull request #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#discussion_r398452200 ## File path: src/runtime/crt/crt_runtime_api.c ## @@ -79,7 +79,7 @@ int

[GitHub] [incubator-tvm] liangfu commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT

liangfu commented on issue #5124: [uTVM][Runtime] Introduce Virtual Memory Allocator to CRT URL: https://github.com/apache/incubator-tvm/pull/5124#issuecomment-604339392 I agree we definitely need an arena style allocator, but can we introduce that in a separate PR? @tqchen

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398520226 ## File path: src/relay/transforms/partition_graph.cc ## @@ -36,36

[GitHub] [incubator-tvm] JishinMaster opened a new issue #5152: ONNX Compatibility

JishinMaster opened a new issue #5152: ONNX Compatibility URL: https://github.com/apache/incubator-tvm/issues/5152 Dear all, - What is the ONNX compatibility of the latest incubator-tvm version? (onnx v1.5?) - Does incubator-tvm supports the classical ML operators described in

[GitHub] [incubator-tvm] mbaret commented on a change in pull request #5134: [RELAY] Add MergeCompilerRegions pass

mbaret commented on a change in pull request #5134: [RELAY] Add MergeCompilerRegions pass URL: https://github.com/apache/incubator-tvm/pull/5134#discussion_r398568581 ## File path: src/relay/transforms/merge_compiler_regions.cc ## @@ -0,0 +1,352 @@ +/* + * Licensed to the

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398590002 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@

[GitHub] [incubator-tvm] manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs

manupa-arm commented on a change in pull request #5143: [RELAY] Re-wrote the Graph Partitioner to support multiple outputs URL: https://github.com/apache/incubator-tvm/pull/5143#discussion_r398590002 ## File path: tests/python/relay/test_pass_partition_graph.py ## @@