[GitHub] [incubator-tvm] anijain2305 commented on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

anijain2305 commented on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#issuecomment-591816179 Thanks for the changes. I will take a deeper look tomorrow.

[GitHub] [incubator-tvm] zhiics commented on issue #4831: [Relay][FrontEnd][MxNet] incorrect data_min_idx and data_max_idx in _qnn_conv

zhiics commented on issue #4831: [Relay][FrontEnd][MxNet] incorrect data_min_idx and data_max_idx in _qnn_conv URL: https://github.com/apache/incubator-tvm/issues/4831#issuecomment-591815321 yeah, it looks flipped to me as well. @shoubhik can you confirm? Thanks.

[GitHub] [incubator-tvm] ANSHUMAN87 opened a new pull request #4951: Conditions updated to cover better user scenarios

ANSHUMAN87 opened a new pull request #4951: Conditions updated to cover better user scenarios URL: https://github.com/apache/incubator-tvm/pull/4951 @tqchen , @ZihengJiang, @jroesch, @merrymercy Sorry if i miss any one who is relevant to this component.

[GitHub] [incubator-tvm] masahi removed a comment on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

masahi removed a comment on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#issuecomment-591802016 thanks @anijain2305 for the review, it is ready to land. Since I'll be asking for your review for my QNN PR, it is a

[GitHub] [incubator-tvm] liangfu commented on issue #3934: [Runtime] MISRA-C compliant TVM runtime

liangfu commented on issue #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#issuecomment-591805463 Thanks for the illustration. I will implement a subset of the functions in `c_runtime_api.h`, which are essential to be able to run a

[GitHub] [incubator-tvm] masahi commented on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

masahi commented on issue #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#issuecomment-591802016 thanks @anijain2305 for the review, it is ready to land. Since I'll be asking for your review for my QNN PR, it is a good

[incubator-tvm] branch master updated (c9be16b -> 9816efc)

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 c9be16b [TUTORIAL] Fix tedd tutorial after strategy change (#4947) add 9816efc

[GitHub] [incubator-tvm] tqchen merged pull request #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files.

tqchen merged pull request #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files. URL: https://github.com/apache/incubator-tvm/pull/4943 This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm-site] branch master updated: Add ASF Links

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 c698b8c Add ASF Links c698b8c is

[incubator-tvm-site] branch asf-site updated: Build at Wed Feb 26 20:06:52 PST 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 1fd0fdf Build at Wed Feb 26

[GitHub] [incubator-tvm] pingsutw opened a new issue #4950: The links not found in Depthwise Convolution tutorial

pingsutw opened a new issue #4950: The links not found in Depthwise Convolution tutorial URL: https://github.com/apache/incubator-tvm/issues/4950 Some links in this [tutorial](https://tvm.apache.org/2017/08/22/Optimize-Deep-Learning-GPU-Operators-with-TVM-A-Depthwise-Convolution-Example)

[incubator-tvm] branch master updated (09c55fd -> c9be16b)

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 09c55fd [VTA] YoloV3 Support (#4887) add c9be16b [TUTORIAL] Fix tedd tutorial after strategy change

[GitHub] [incubator-tvm] tqchen merged pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

tqchen merged pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947 This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4927: [Relay][Pass] Add inline pass

zhiics commented on a change in pull request #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#discussion_r384852268 ## File path: src/relay/pass/inline.cc ## @@ -0,0 +1,227 @@ +/* + * Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] jmorrill commented on a change in pull request #4857: Windows Support for cpp_rpc

jmorrill commented on a change in pull request #4857: Windows Support for cpp_rpc URL: https://github.com/apache/incubator-tvm/pull/4857#discussion_r384841512 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -20,141 +20,139 @@ * \file rpc_env.cc * \brief Server environment

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass

anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#discussion_r384842170 ## File path: src/relay/pass/inline.cc ## @@ -0,0 +1,227 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #4949: Conv3D ONNX support and conv3D_ncdhw x86 schedules

icemelon9 commented on a change in pull request #4949: Conv3D ONNX support and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384841548 ## File path: topi/python/topi/x86/conv3d.py ## @@ -110,6 +146,44 @@ def _traverse(op):

[GitHub] [incubator-tvm] jmorrill commented on a change in pull request #4857: Windows Support for cpp_rpc

jmorrill commented on a change in pull request #4857: Windows Support for cpp_rpc URL: https://github.com/apache/incubator-tvm/pull/4857#discussion_r384841512 ## File path: apps/cpp_rpc/rpc_env.cc ## @@ -20,141 +20,139 @@ * \file rpc_env.cc * \brief Server environment

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #4949: Conv3D ONNX support and conv3D_ncdhw x86 schedules

icemelon9 commented on a change in pull request #4949: Conv3D ONNX support and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384841079 ## File path: topi/python/topi/x86/conv3d.py ## @@ -197,6 +273,92 @@ def

[GitHub] [incubator-tvm] mbrookhart commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

mbrookhart commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#issuecomment-591705734 Thanks, @anijain2305 and @icemelon9! I missed the change in testing strategy when I rebased ontop of @icemelon9 's recent

[GitHub] [incubator-tvm] kumasento commented on issue #4847: Return empty CSourceModule when no lowered_funcs exists in Relay mod

kumasento commented on issue #4847: Return empty CSourceModule when no lowered_funcs exists in Relay mod URL: https://github.com/apache/incubator-tvm/pull/4847#issuecomment-591705619 Yes, I will do that very soon, was trapped at a conference. Sorry for the delay. On Wed, 26 Feb

[GitHub] [incubator-tvm] mbrookhart commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

mbrookhart commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384838550 ## File path: topi/python/topi/x86/conv3d.py ## @@ -197,6 +273,92 @@ def

[GitHub] [incubator-tvm] tqchen commented on issue #4831: [Relay][FrontEnd][MxNet] incorrect data_min_idx and data_max_idx in _qnn_conv

tqchen commented on issue #4831: [Relay][FrontEnd][MxNet] incorrect data_min_idx and data_max_idx in _qnn_conv URL: https://github.com/apache/incubator-tvm/issues/4831#issuecomment-591704766 cc @kevinthesun @zhiics can you help check on this ?

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4887: [VTA] YoloV3 Support

tmoreau89 commented on issue #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#issuecomment-591704294 Thank you @huajsj @cbalint13 @liangfu , the code has been merged! This is an automated

[GitHub] [incubator-tvm] tqchen commented on issue #4523: Optimization for subpixel layer on Tensor core

tqchen commented on issue #4523: Optimization for subpixel layer on Tensor core URL: https://github.com/apache/incubator-tvm/issues/4523#issuecomment-591704272 Close for now as depth2space is implemented. Please feel free to open new threads, or create discussions on the forum

[incubator-tvm] branch master updated (8e7e779 -> 09c55fd)

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 8e7e779 [Frontend][TFLite] Add parser support for 'square' operator (#4915) add 09c55fd [VTA] YoloV3

[GitHub] [incubator-tvm] tmoreau89 merged pull request #4887: [VTA] YoloV3 Support

tmoreau89 merged pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] tqchen closed issue #4523: Optimization for subpixel layer on Tensor core

tqchen closed issue #4523: Optimization for subpixel layer on Tensor core URL: https://github.com/apache/incubator-tvm/issues/4523 This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen closed issue #3874: [Relay] [RFC] is_cons, unpack_cons, is_s, unpack_s

tqchen closed issue #3874: [Relay] [RFC] is_cons, unpack_cons, is_s, unpack_s URL: https://github.com/apache/incubator-tvm/issues/3874 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on issue #3874: [Relay] [RFC] is_cons, unpack_cons, is_s, unpack_s

tqchen commented on issue #3874: [Relay] [RFC] is_cons, unpack_cons, is_s, unpack_s URL: https://github.com/apache/incubator-tvm/issues/3874#issuecomment-591703861 close for now due to inactive status, feel free to open a new thread

[GitHub] [incubator-tvm] tqchen commented on issue #4122: [Relay][Topi] Conv NHWC pack int8 kernel layout

tqchen commented on issue #4122: [Relay][Topi] Conv NHWC pack int8 kernel layout URL: https://github.com/apache/incubator-tvm/issues/4122#issuecomment-591703635 close for now as the relevant PR get merged. Let us open a new thread for new items

[GitHub] [incubator-tvm] tqchen closed issue #4122: [Relay][Topi] Conv NHWC pack int8 kernel layout

tqchen closed issue #4122: [Relay][Topi] Conv NHWC pack int8 kernel layout URL: https://github.com/apache/incubator-tvm/issues/4122 This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen closed issue #3501: [RFC][Relay][HalideIR] Automatically generate the AST

tqchen closed issue #3501: [RFC][Relay][HalideIR] Automatically generate the AST URL: https://github.com/apache/incubator-tvm/issues/3501 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on issue #3501: [RFC][Relay][HalideIR] Automatically generate the AST

tqchen commented on issue #3501: [RFC][Relay][HalideIR] Automatically generate the AST URL: https://github.com/apache/incubator-tvm/issues/3501#issuecomment-591703330 close for now due to inactive status, @yzhliu will followup once he have a more specific proposal

[GitHub] [incubator-tvm] tqchen commented on issue #4857: Windows Support for cpp_rpc

tqchen commented on issue #4857: Windows Support for cpp_rpc URL: https://github.com/apache/incubator-tvm/pull/4857#issuecomment-591702537 @soiferj @FrozenGene please followup, and https://docs.tvm.ai/contribute/code_review.html#approve-and-request-changes-explicitly

[GitHub] [incubator-tvm] tqchen commented on issue #4704: [Relay][Frontend][TFLite] Add parser support for arg_min_max

tqchen commented on issue #4704: [Relay][Frontend][TFLite] Add parser support for arg_min_max URL: https://github.com/apache/incubator-tvm/pull/4704#issuecomment-591702122 ping @inadob @anijain2305 please followup This is an

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

tqchen commented on issue #4788: [FRONTEND][TFLITE]Gather, StridedSlice op support added URL: https://github.com/apache/incubator-tvm/pull/4788#issuecomment-591701888 ping @siju-samuel please followup on the review comments @FrozenGene @wyc-ruiker please

[incubator-tvm] branch master updated (502ab60 -> 8e7e779)

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 502ab60 Remove SGX toolchain installation from CI Dockerfile (#4948) add 8e7e779 [Frontend][TFLite]

[GitHub] [incubator-tvm] tqchen merged pull request #4915: [Frontend][TFLite] Add parser support for 'square' operator

tqchen merged pull request #4915: [Frontend][TFLite] Add parser support for 'square' operator URL: https://github.com/apache/incubator-tvm/pull/4915 This is an automated message from the Apache Git Service. To respond to

[GitHub] [incubator-tvm] tqchen commented on issue #4828: [QNN][TFLite] TFLite rounding mode support

tqchen commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-591701322 ping @LiangHao151941 please followup This is an automated message from

[GitHub] [incubator-tvm] tqchen commented on issue #4915: [Frontend][TFLite] Add parser support for 'square' operator

tqchen commented on issue #4915: [Frontend][TFLite] Add parser support for 'square' operator URL: https://github.com/apache/incubator-tvm/pull/4915#issuecomment-591701499 Thanks @inadob @wyc-ruiker ! This is an automated

[GitHub] [incubator-tvm] tqchen commented on issue #4805: [Frontend][TFlite] Add parser support for relu6, leaky_relu, relu_n1_to_1, log_softmax

tqchen commented on issue #4805: [Frontend][TFlite] Add parser support for relu6, leaky_relu, relu_n1_to_1, log_softmax URL: https://github.com/apache/incubator-tvm/pull/4805#issuecomment-591701219 @inadob please followup to address the review comments :)

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4927: [Relay][Pass] Add inline pass

zhiics commented on a change in pull request #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#discussion_r384831872 ## File path: src/relay/pass/inline.cc ## @@ -0,0 +1,227 @@ +/* + * Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] gmagogsfm commented on a change in pull request #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime

gmagogsfm commented on a change in pull request #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime URL: https://github.com/apache/incubator-tvm/pull/4459#discussion_r384829809 ## File path: src/contrib/tf_op/tvm_dso_ops.cc ## @@ -0,0 +1,89 @@ +/* +

[GitHub] [incubator-tvm] gmagogsfm commented on a change in pull request #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime

gmagogsfm commented on a change in pull request #4459: [RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime URL: https://github.com/apache/incubator-tvm/pull/4459#discussion_r384829391 ## File path: src/contrib/tf_op/tvm_dso_op_kernels.cc ## @@ -0,0 +1,309

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4887: [VTA] YoloV3 Support

tmoreau89 commented on issue #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#issuecomment-591695374 Thanks @huajsj , I merged https://github.com/uwsampl/tvm-distro/pull/17 This is an

[GitHub] [incubator-tvm] huajsj commented on issue #4887: [VTA] YoloV3 Support

huajsj commented on issue #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#issuecomment-591690697 @tmoreau89 , Thanks for the kindly follow up, 'uwsampl/tvm-distro#17' is the the default Autotvm configure file for Yolov3 tiny, could you help to review

[GitHub] [incubator-tvm] tqchen commented on issue #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files.

tqchen commented on issue #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files. URL: https://github.com/apache/incubator-tvm/pull/4943#issuecomment-591690100 cc @icemelon9 @yzhliu This is an automated message from

[GitHub] [incubator-tvm] tqchen edited a comment on issue #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files.

tqchen edited a comment on issue #4943: [REFACTOR][PY][API-CHANGE] Remove legacy python files. URL: https://github.com/apache/incubator-tvm/pull/4943#issuecomment-591690100 cc @icemelon9 @yzhliu @ZihengJiang This is an

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass

anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#discussion_r384817529 ## File path: src/relay/pass/inline.cc ## @@ -0,0 +1,227 @@ +/* + * Licensed to the Apache Software

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass

anijain2305 commented on a change in pull request #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#discussion_r384813972 ## File path: include/tvm/relay/expr.h ## @@ -221,6 +221,13 @@ class FunctionNode : public BaseFuncNode {

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384806750 ## File path: topi/python/topi/x86/conv3d.py ## @@ -73,6 +73,45 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

anijain2305 commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#issuecomment-591681153 @alexgl-github You might be interested in this. This is

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384807143 ## File path: topi/python/topi/x86/conv3d.py ## @@ -110,6 +149,43 @@ def _traverse(op):

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

anijain2305 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384806231 ## File path: python/tvm/relay/frontend/onnx.py ## @@ -99,8 +99,10 @@ def _impl(attr):

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

zhiics commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#discussion_r384807129 ## File path: python/tvm/relay/transform.py ## @@ -179,6 +180,17 @@ def SimplifyInference():

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4942: Move Ops in relay.op.contrib.*

comaniac commented on a change in pull request #4942: Move Ops in relay.op.contrib.* URL: https://github.com/apache/incubator-tvm/pull/4942#discussion_r384806533 ## File path: python/tvm/relay/op/nn/_nn.py ## @@ -246,6 +246,15 @@ def legalize_conv2d_transpose(attrs,

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #4942: Move Ops in relay.op.contrib.*

icemelon9 commented on a change in pull request #4942: Move Ops in relay.op.contrib.* URL: https://github.com/apache/incubator-tvm/pull/4942#discussion_r384805514 ## File path: python/tvm/relay/op/nn/_nn.py ## @@ -246,6 +246,15 @@ def legalize_conv2d_transpose(attrs,

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

icemelon9 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384804848 ## File path: topi/python/topi/x86/conv3d.py ## @@ -197,6 +273,92 @@ def

[GitHub] [incubator-tvm] icemelon9 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

icemelon9 commented on a change in pull request #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#discussion_r384804363 ## File path: topi/python/topi/x86/conv3d.py ## @@ -73,6 +73,45 @@ def conv3d_ndhwc(cfg,

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

anijain2305 commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#discussion_r384804850 ## File path: tests/python/relay/test_pass_fast_math.py ## @@ -0,0 +1,52 @@ +# Licensed

[GitHub] [incubator-tvm] zhiics commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

zhiics commented on a change in pull request #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#discussion_r384803727 ## File path: tests/python/relay/test_pass_fast_math.py ## @@ -0,0 +1,52 @@ +# Licensed to

[GitHub] [incubator-tvm] tqchen commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules

tqchen commented on issue #4949: Conv3D ONNX supprot and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#issuecomment-591672116 also cc @yzhliu @icemelon9 @anijain2305 @masahi This is an

[incubator-tvm] branch master updated (eba50ad -> 502ab60)

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 eba50ad [Relay][pass] call graph for relay (#4922) add 502ab60 Remove SGX toolchain installation from

[GitHub] [incubator-tvm] tqchen merged pull request #4948: Remove SGX toolchain installation from CI Dockerfile

tqchen merged pull request #4948: Remove SGX toolchain installation from CI Dockerfile URL: https://github.com/apache/incubator-tvm/pull/4948 This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] tqchen closed issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file

tqchen closed issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file URL: https://github.com/apache/incubator-tvm/issues/4946 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

masahi commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#discussion_r384779098 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -1016,17 +978,58 @@ def

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384772459 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384772555 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] mbrookhart opened a new pull request #4949: Conv3D_ncdhw and onnx support

mbrookhart opened a new pull request #4949: Conv3D_ncdhw and onnx support URL: https://github.com/apache/incubator-tvm/pull/4949 This PR adds support for conv3d to the ONNX frontend and ports the conv2d_nchw schedules to conv3d_ncdhw for improved performance. Thanks! cc:

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384731000 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software Foundation

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384730458 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape): return

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384730128 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape): return

[GitHub] [incubator-tvm] huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support

huajsj commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384729332 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape): return

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384722553 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape):

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384724003 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384722395 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape):

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384722597 ## File path: vta/python/vta/top/graphpack.py ## @@ -55,6 +57,46 @@ def _unpack_batch_channel(data, old_shape):

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384724511 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384724334 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support

tmoreau89 commented on a change in pull request #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#discussion_r384724257 ## File path: vta/tutorials/frontend/deploy_detection.py ## @@ -0,0 +1,332 @@ +# Licensed to the Apache Software

[GitHub] [incubator-tvm] huajsj commented on issue #4887: [VTA] YoloV3 Support

huajsj commented on issue #4887: [VTA] YoloV3 Support URL: https://github.com/apache/incubator-tvm/pull/4887#issuecomment-591599184 @tmoreau89 , if you have time , could you help to have reivew? thanks. This is an automated

[GitHub] [incubator-tvm] nhynes edited a comment on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file

nhynes edited a comment on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file URL: https://github.com/apache/incubator-tvm/issues/4946#issuecomment-591574746 hmm, I'll fix this now. SGX is unfortunately quite deprecated at this time () and I think

[GitHub] [incubator-tvm] zhiics commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

zhiics commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#issuecomment-591579992 Yes, I am okay to use required_pass for now. This is an

[GitHub] [incubator-tvm] nhynes opened a new pull request #4948: Remove SGX toolchain installation from CI Dockerfile

nhynes opened a new pull request #4948: Remove SGX toolchain installation from CI Dockerfile URL: https://github.com/apache/incubator-tvm/pull/4948 This is an automated message from the Apache Git Service. To respond to the

[GitHub] [incubator-tvm] tqchen commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

tqchen commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#issuecomment-591579730 It is a bit pre-mature to introduce additional opt levels as we add passes. how about we only support the `required_pass` option

[GitHub] [incubator-tvm] anijain2305 commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

anijain2305 commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#issuecomment-591578182 @zhiics I agree we need more clarity over the usage of opt_level=4. Thinking more about this, I feel that opt_level=4 is

[GitHub] [incubator-tvm] nhynes commented on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file

nhynes commented on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file URL: https://github.com/apache/incubator-tvm/issues/4946#issuecomment-591574746 hmm, I'll fix this now. SGX is unfortunately quite deprecated at this time () and I think it

[GitHub] [incubator-tvm] zhiics commented on issue #4927: [Relay][Pass] Add inline pass

zhiics commented on issue #4927: [Relay][Pass] Add inline pass URL: https://github.com/apache/incubator-tvm/pull/4927#issuecomment-591572184 cc @tqchen @jroesch @icemelon9 @yzhliu @anijain2305 @mbaret @masahi @soiferj This

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#discussion_r384668865 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -1016,17 +978,58 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#discussion_r384674817 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -718,293 +732,241 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#discussion_r384667422 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -718,293 +732,241 @@ def

[GitHub] [incubator-tvm] anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend

anijain2305 commented on a change in pull request #4944: [Relay, Torch] Clean up and refactor PyTorch frontend URL: https://github.com/apache/incubator-tvm/pull/4944#discussion_r384674386 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -1016,17 +978,58 @@ def

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947#discussion_r384670177 ## File path: tutorials/language/tedd.py ## @@ -1,42 +1,42 @@ -# Licensed to the Apache

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947#discussion_r384670790 ## File path: tutorials/language/tedd.py ## @@ -63,102 +63,102 @@ A =

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947#discussion_r384670913 ## File path: tutorials/language/tedd.py ## @@ -63,102 +63,102 @@ A =

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947#discussion_r384668104 ## File path: tutorials/language/tedd.py ## @@ -63,102 +63,102 @@ A =

[GitHub] [incubator-tvm] comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change

comaniac commented on a change in pull request #4947: [TUTORIAL] Fix tedd tutorial after strategy change URL: https://github.com/apache/incubator-tvm/pull/4947#discussion_r384670554 ## File path: tutorials/language/tedd.py ## @@ -1,42 +1,42 @@ -# Licensed to the Apache

[GitHub] [incubator-tvm] tqchen commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh

tqchen commented on issue #4873: [Relay][FastMath] Relay pass to use fast exp/tanh URL: https://github.com/apache/incubator-tvm/pull/4873#issuecomment-591563137 Seems `with relay.build_config(opt_level=3, required_pass=['FastMath'])` is simple enough that we can go with that for now

[GitHub] [incubator-tvm] tqchen commented on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file

tqchen commented on issue #4946: [CI][Docker] ubuntu_install_sgx.sh breaks when trying to download patch file URL: https://github.com/apache/incubator-tvm/issues/4946#issuecomment-591561971 cc @nhynes This is an automated

  1   2   >