[GitHub] [incubator-tvm] ANSHUMAN87 opened a new pull request #4989: Docs and Readme updated as per new namespace change

ANSHUMAN87 opened a new pull request #4989: Docs and Readme updated as per new namespace change URL: https://github.com/apache/incubator-tvm/pull/4989 Thanks for contributing to TVM! Please refer to guideline https://docs.tvm.ai/contribute/ for useful information and tips. After the

[GitHub] [incubator-tvm] lfengad closed pull request #4882: [Relay][Topi] Hashtable support

lfengad closed pull request #4882: [Relay][Topi] Hashtable support URL: https://github.com/apache/incubator-tvm/pull/4882 This is an automated message from the Apache Git Service. To respond to the message, please log on to

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r388107817 ## File path: apps/bundle_deploy_c/runtime.c ## @@ -0,0 +1,42 @@ +/* + * Licensed to the Apache

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r388107841 ## File path: src/runtime/crt/load_json.c ## @@ -0,0 +1,359 @@ +/* + * Licensed to the Apache Software

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

liangfu edited a comment on issue #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#issuecomment-595059148 > Also is this MISRA-C compliant going to work on 32bit and 64bit systems? I have tested this on both 32-bit ARM board, and

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

liangfu commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r388107012 ## File path: apps/bundle_deploy_c/README.md ## @@ -0,0 +1,53 @@ + + + + + + + + + + + + + + + + + +

[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-595059148 > Also is this MISRA-C compliant going to work on 32bit and 64bit systems? I have tested this on both 32-bit ARM board, and 64-bit

[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-595053967 @tqchen @tmoreau89 Thanks for checking out. I made the demo merged into an existing directory `apps/bundle_deploy`, and now the proposed

[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_r388100662 ## File path: src/contrib/tf_op/tvm_dso_ops.cc ## @@ -0,0 +1,89 @@ +/* +

[GitHub] [incubator-tvm] Laurawly commented on issue #4901: [Fix] Fix get_valid_count flaky test for cuda

Laurawly commented on issue #4901: [Fix] Fix get_valid_count flaky test for cuda URL: https://github.com/apache/incubator-tvm/pull/4901#issuecomment-595041890 @masahi That’s weird. You can comment off the test for now and I’ll try to reproduce it on my end.

[GitHub] [incubator-tvm] masahi commented on issue #4901: [Fix] Fix get_valid_count flaky test for cuda

masahi commented on issue #4901: [Fix] Fix get_valid_count flaky test for cuda URL: https://github.com/apache/incubator-tvm/pull/4901#issuecomment-595040094 @Laurawly I still get a flaky failure from get_valid_count test in my PR

[GitHub] [incubator-tvm] masahi commented on issue #4987: [Relay] Reduce plevel of conv2d winograd implementation on cuda

masahi commented on issue #4987: [Relay] Reduce plevel of conv2d winograd implementation on cuda URL: https://github.com/apache/incubator-tvm/pull/4987#issuecomment-595036072 I think it's better to wait until the commit author issue is resolved

[GitHub] [incubator-tvm] masahi commented on issue #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on issue #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#issuecomment-595030851 Let's wait until the commit author issue is resolved

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

wrongtest 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_r388071666 ## File path: src/contrib/tf_op/tvm_dso_ops.cc ## @@ -0,0 +1,89 @@ +/* +

[GitHub] [incubator-tvm] zhiics commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule

zhiics commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule URL: https://github.com/apache/incubator-tvm/pull/4988#issuecomment-595008776 @wweic Its okay. Tutorials have already used module.

[GitHub] [incubator-tvm] wweic commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule

wweic commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule URL: https://github.com/apache/incubator-tvm/pull/4988#issuecomment-595008421 LGTM. Should we also update the tutorials? This is

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388056496 ## File path: vta/src/de10nano/de10nano_mgr.h ## @@ -0,0 +1,554 @@ +/* + * Licensed

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388051460 ## File path: vta/hardware/chisel/Makefile ## @@ -32,16 +32,19 @@ ifeq (,

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388053279 ## File path: vta/hardware/chisel/src/main/scala/core/TensorLoad.scala ## @@ -212,14

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388057224 ## File path: vta/tests/python/de10nano/test_program_rpc.py ## @@ -0,0 +1,45 @@ +#

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388056182 ## File path: vta/src/de10nano/de10nano_mgr.h ## @@ -0,0 +1,554 @@ +/* + * Licensed

[GitHub] [incubator-tvm] liangfu commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594992227 > This makes me realize that we may want to run CI testing for different FPGA parameterizations in TSIM, e.g. DE10Nano,

[GitHub] [incubator-tvm] liangfu commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

liangfu commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388042452 ## File path: vta/hardware/chisel/Makefile ## @@ -109,7 +133,7 @@ else lib_path =

[GitHub] [incubator-tvm] vv1133 commented on issue #4980: [FRONTEND][TENSORFLOW] support multiply outputs

vv1133 commented on issue #4980: [FRONTEND][TENSORFLOW] support multiply outputs URL: https://github.com/apache/incubator-tvm/pull/4980#issuecomment-594982726 > Can you add a unit test? @zhiics There was `multi_output` test case in test_forward.py before，but it didn't test

[GitHub] [incubator-tvm] pasqoc commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594980581 I have produced the following table while testing the various targets under same workloads. Where you see nan it

[GitHub] [incubator-tvm] pasqoc commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388027401 ## File path: vta/hardware/chisel/Makefile ## @@ -109,7 +133,7 @@ else lib_path =

[GitHub] [incubator-tvm] pasqoc commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594974692 I have tested unit tests, conv2d, and deploy classification for tsim and de10 for Chisel with De10Config only.

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388025984 ## File path: vta/hardware/chisel/Makefile ## @@ -109,7 +133,7 @@ else lib_path

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388026025 ## File path: cmake/modules/VTA.cmake ## @@ -101,7 +101,9 @@ elseif(PYTHON)

[GitHub] [incubator-tvm] pasqoc commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388025042 ## File path: vta/hardware/chisel/Makefile ## @@ -32,16 +32,19 @@ ifeq (,

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594973729 @vegaluisjose @liangfu this makes me realize that we may want to run CI testing for different FPGA parameterizations

[GitHub] [incubator-tvm] pasqoc commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388023813 ## File path: vta/hardware/chisel/Makefile ## @@ -109,7 +133,7 @@ else lib_path =

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388021612 ## File path: vta/hardware/chisel/Makefile ## @@ -32,16 +32,19 @@ ifeq (,

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388021304 ## File path: vta/hardware/chisel/Makefile ## @@ -109,7 +133,7 @@ else lib_path

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388021044 ## File path: cmake/modules/VTA.cmake ## @@ -101,7 +101,9 @@ elseif(PYTHON)

[GitHub] [incubator-tvm] pasqoc commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388021605 ## File path: cmake/modules/VTA.cmake ## @@ -101,7 +101,9 @@ elseif(PYTHON)

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on a change in pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#discussion_r388021044 ## File path: cmake/modules/VTA.cmake ## @@ -101,7 +101,9 @@ elseif(PYTHON)

[GitHub] [incubator-tvm] tmoreau89 commented on issue #3934: [Runtime] MISRA-C compliant TVM runtime

tmoreau89 commented on issue #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#issuecomment-594969599 One additional suggestion I had was to test that the demo builds and runs in CI; a quick spot check on your branch of building the demo

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r388018716 ## File path: src/runtime/crt/load_json.c ## @@ -0,0 +1,359 @@ +/* + * Licensed to the Apache

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r387995155 ## File path: apps/bundle_deploy_c/README.md ## @@ -0,0 +1,53 @@ + + + + + + + + + + + + + + + + + +

[GitHub] [incubator-tvm] tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime

tmoreau89 commented on a change in pull request #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#discussion_r387995703 ## File path: apps/bundle_deploy_c/runtime.c ## @@ -0,0 +1,42 @@ +/* + * Licensed to the Apache

[GitHub] [incubator-tvm] tqchen closed issue #4950: The links not found in Depthwise Convolution tutorial

tqchen closed issue #4950: The links not found in Depthwise Convolution tutorial URL: https://github.com/apache/incubator-tvm/issues/4950 This is an automated message from the Apache Git Service. To respond to the message,

[GitHub] [incubator-tvm] tqchen commented on issue #4950: The links not found in Depthwise Convolution tutorial

tqchen commented on issue #4950: The links not found in Depthwise Convolution tutorial URL: https://github.com/apache/incubator-tvm/issues/4950#issuecomment-594967822 The pr has been merged This is an automated message from

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

tqchen commented on issue #4949: Conv3D ONNX support and conv3D_ncdhw x86 schedules URL: https://github.com/apache/incubator-tvm/pull/4949#issuecomment-594966265 @icemelon9 please followup This is an automated message from

[incubator-tvm] branch master updated: Conditions updated to cover better user scenarios (#4951)

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.git The following commit(s) were added to refs/heads/master by this push: new fe74b37 Conditions updated to cover

[GitHub] [incubator-tvm] tqchen merged pull request #4951: Conditions updated to cover better user scenarios

tqchen merged pull request #4951: Conditions updated to cover better user scenarios URL: https://github.com/apache/incubator-tvm/pull/4951 This is an automated message from the Apache Git Service. To respond to the message,

[incubator-tvm] branch master updated: Fix gpu not found when running TVM docker (#4975)

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.git The following commit(s) were added to refs/heads/master by this push: new 7a06bbe Fix gpu not found when running

[GitHub] [incubator-tvm] tqchen merged pull request #4975: Fix gpu not found when running TVM docker

tqchen merged pull request #4975: Fix gpu not found when running TVM docker URL: https://github.com/apache/incubator-tvm/pull/4975 This is an automated message from the Apache Git Service. To respond to the message, please

[GitHub] [incubator-tvm] tqchen commented on issue #4976: Revive the Rust + SGX refactor

tqchen commented on issue #4976: Revive the Rust + SGX refactor URL: https://github.com/apache/incubator-tvm/pull/4976#issuecomment-594965008 let us aim to merge it in a week This is an automated message from the Apache Git

[GitHub] [incubator-tvm] comaniac commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule

comaniac commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule URL: https://github.com/apache/incubator-tvm/pull/4988#issuecomment-594964479 I see. That makes sense. This is an automated

[GitHub] [incubator-tvm] zhiics commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule

zhiics commented on issue #4988: [Refactor][Relay Build] refactor build module to take IRModule URL: https://github.com/apache/incubator-tvm/pull/4988#issuecomment-594962642 Yeah, Python side still accepts `Function` as well. Its just a line of code `tvm::IRModule::FromExpr(func);` in

[GitHub] [incubator-tvm] zhiics opened a new pull request #4988: [Refactor][Relay Build] refactor build module to take IRModule

zhiics opened a new pull request #4988: [Refactor][Relay Build] refactor build module to take IRModule URL: https://github.com/apache/incubator-tvm/pull/4988 This PR refactors relay build_module interfaces to accept IRModules instead of Function. This can help external codegen that may

[GitHub] [incubator-tvm] pasqoc commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594935354 You are welcome! Sorry I forgot to lint, doing next.

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594917196 Thank you @pasqoc for this awesome PR, and extensive fixes to the Chisel codebase. @liangfu , @vegaluisjose and I will

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

tmoreau89 commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594916203 @vegaluisjose can you also review this PR? This is an

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4628: [Object] Add String container

tqchen commented on a change in pull request #4628: [Object] Add String container URL: https://github.com/apache/incubator-tvm/pull/4628#discussion_r387972834 ## File path: tests/cpp/container_test.cc ## @@ -221,11 +222,154 @@ TEST(Map, Iterator) { using namespace tvm;

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4628: [Object] Add String container

tqchen commented on a change in pull request #4628: [Object] Add String container URL: https://github.com/apache/incubator-tvm/pull/4628#discussion_r387973349 ## File path: tests/cpp/container_test.cc ## @@ -221,11 +222,154 @@ TEST(Map, Iterator) { using namespace tvm;

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4628: [Object] Add String container

tqchen commented on a change in pull request #4628: [Object] Add String container URL: https://github.com/apache/incubator-tvm/pull/4628#discussion_r387973867 ## File path: include/tvm/runtime/container.h ## @@ -274,7 +304,286 @@ class ADT : public ObjectRef {

[GitHub] [incubator-tvm] tqchen commented on a change in pull request #4628: [Object] Add String container

tqchen commented on a change in pull request #4628: [Object] Add String container URL: https://github.com/apache/incubator-tvm/pull/4628#discussion_r387974187 ## File path: include/tvm/runtime/container.h ## @@ -274,7 +304,286 @@ class ADT : public ObjectRef {

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4964: [Torch] Add initial control flow support

masahi commented on a change in pull request #4964: [Torch] Add initial control flow support URL: https://github.com/apache/incubator-tvm/pull/4964#discussion_r387973444 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -614,6 +615,55 @@ def _impl(inputs,

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4964: [Torch] Add initial control flow support

masahi commented on a change in pull request #4964: [Torch] Add initial control flow support URL: https://github.com/apache/incubator-tvm/pull/4964#discussion_r387973444 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -614,6 +615,55 @@ def _impl(inputs,

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4964: [Torch] Add initial control flow support

masahi commented on a change in pull request #4964: [Torch] Add initial control flow support URL: https://github.com/apache/incubator-tvm/pull/4964#discussion_r387973444 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -614,6 +615,55 @@ def _impl(inputs,

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#discussion_r387959144 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -458,7 +458,10 @@ def

[GitHub] [incubator-tvm] icemelon9 opened a new pull request #4987: [Relay] Reduce plevel of conv2d winograd implementation on cuda

icemelon9 opened a new pull request #4987: [Relay] Reduce plevel of conv2d winograd implementation on cuda URL: https://github.com/apache/incubator-tvm/pull/4987 Fix issue https://discuss.tvm.ai/t/performance-has-been-too-slow-since-the-tvm-update/5865

[GitHub] [incubator-tvm] pyjhzwh commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

pyjhzwh commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#discussion_r387954278 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -458,7 +458,10 @@ def

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#discussion_r387936352 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -458,7 +458,10 @@ def

[GitHub] [incubator-tvm] masahi edited a comment on issue #4977: [Torch, QNN] Add support for quantized models via QNN

masahi edited a comment on issue #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977#issuecomment-594821500 Hmm for some reason, this commit became @anijain2305' commit.

[GitHub] [incubator-tvm] masahi edited a comment on issue #4977: [Torch, QNN] Add support for quantized models via QNN

masahi edited a comment on issue #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977#issuecomment-594821500 Hmm for some reason, this commit became @anijain2305' commit.

[GitHub] [incubator-tvm] masahi commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN

masahi commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977#issuecomment-594821500 Hmm for some reason, this commit became @anijain2305' commit.

[GitHub] [incubator-tvm] pasqoc commented on issue #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc commented on issue #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986#issuecomment-594816587 Hi @tmoreau89, @liangfu, please review the PR and let me know of anything. Finally deploy classification returns a cat

[GitHub] [incubator-tvm] masahi commented on issue #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on issue #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#issuecomment-594808062 Please add a test case. Add your test below.

[GitHub] [incubator-tvm] pasqoc opened a new pull request #4986: [VTA][Chisel, de10nano] Chisel fixes and de10nano support

pasqoc opened a new pull request #4986: [VTA][Chisel,de10nano] Chisel fixes and de10nano support URL: https://github.com/apache/incubator-tvm/pull/4986 This PR provides fixes to the VTA Chisel implementation, as well as support and enhancements for the tsim and de10nano targets.

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#discussion_r387899300 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -918,7 +921,7 @@ def

[GitHub] [incubator-tvm] masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

masahi commented on a change in pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984#discussion_r387899300 ## File path: python/tvm/relay/frontend/pytorch.py ## @@ -918,7 +921,7 @@ def

[GitHub] [incubator-tvm] jmorrill opened a new pull request #4985: Implemented kDLCPUPinned (cudaMallocHost)

jmorrill opened a new pull request #4985: Implemented kDLCPUPinned (cudaMallocHost) URL: https://github.com/apache/incubator-tvm/pull/4985 Data allocated via cudaMallocHost is supposed to be faster at transferring data to/from a cuda device, and it was not implemented in the tvm runtime.

[GitHub] [incubator-tvm] pyjhzwh opened a new pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool

pyjhzwh opened a new pull request #4984: Fix stride default value None in torch.nn.functional.avg_pool URL: https://github.com/apache/incubator-tvm/pull/4984 The default value of stride in nn.functional.avg_pool is set as None,

[GitHub] [incubator-tvm] wpan11nv commented on issue #4983: [CodeGen][CUDA] Enhance CUDA codegen for SelectNode

wpan11nv commented on issue #4983: [CodeGen][CUDA] Enhance CUDA codegen for SelectNode URL: https://github.com/apache/incubator-tvm/pull/4983#issuecomment-594786914 The test fails without this patch. It is also exposed by https://github.com/apache/incubator-tvm/pull/4968, in which a

[GitHub] [incubator-tvm] wpan11nv opened a new pull request #4983: [CodeGen][CUDA] Enhance CUDA codegen for SelectNode

wpan11nv opened a new pull request #4983: [CodeGen][CUDA] Enhance CUDA codegen for SelectNode URL: https://github.com/apache/incubator-tvm/pull/4983 - This patch allows CUDA backend to emit correct code for selects with vector conditions, which may be produced by floordiv op

[GitHub] [incubator-tvm] notoraptor commented on issue #4938: [topi][relay] add operation tan to TVM

notoraptor commented on issue #4938: [topi][relay] add operation tan to TVM URL: https://github.com/apache/incubator-tvm/pull/4938#issuecomment-594780516 @kevinthesun Tests passed ! I implemented tan in LLVM using `sin/cos` and I fixed CUDA implementation by using `tanf` instead of

[GitHub] [incubator-tvm] anijain2305 commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN

anijain2305 commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977#issuecomment-594774078 Thanks @masahi @jwfromm This is merged! This is an

[GitHub] [incubator-tvm] anijain2305 merged pull request #4977: [Torch, QNN] Add support for quantized models via QNN

anijain2305 merged pull request #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977 This is an automated message from the Apache Git Service. To respond to the

[incubator-tvm] branch master updated: [Torch, QNN] Add support for quantized models via QNN (#4977)

This is an automated email from the ASF dual-hosted git repository. anijain2305 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 fc7f078 [Torch, QNN] Add support

[GitHub] [incubator-tvm] yongfeng-nv commented on issue #4931: Tighten split's extent

yongfeng-nv commented on issue #4931: Tighten split's extent URL: https://github.com/apache/incubator-tvm/pull/4931#issuecomment-594748097 @merrymercy, I have made your recommended changes. Please review it again. Can you share your use case hitting this issue? @tqchen, the flaky

[incubator-tvm] branch master updated: Tighten split's extent (#4931)

This is an automated email from the ASF dual-hosted git repository. lmzheng 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 585f9ce Tighten split's extent (#4931)

[GitHub] [incubator-tvm] merrymercy merged pull request #4931: Tighten split's extent

merrymercy merged pull request #4931: Tighten split's extent URL: https://github.com/apache/incubator-tvm/pull/4931 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub

[GitHub] [incubator-tvm] masahi commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN

masahi commented on issue #4977: [Torch, QNN] Add support for quantized models via QNN URL: https://github.com/apache/incubator-tvm/pull/4977#issuecomment-594733544 @anijain2305 I think it is a good time to land it. This is

[incubator-tvm-site] branch asf-site updated: Build at Wed Mar 4 10:58:39 CST 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 89e5aa6 Build at Wed Mar 4

[GitHub] [incubator-tvm] leandron commented on issue #4965: [CI][Docker] pin xgboost dependency version to 0.90

leandron commented on issue #4965: [CI][Docker] pin xgboost dependency version to 0.90 URL: https://github.com/apache/incubator-tvm/pull/4965#issuecomment-594568212 Thanks @tqchen. I'll see to provide @hcho3 with instruction on how to reproduce the issue I see on xgboost.

[GitHub] [incubator-tvm] ANSHUMAN87 commented on issue #4534: [Relay] Dead code elimination pass blows up call stack

ANSHUMAN87 commented on issue #4534: [Relay] Dead code elimination pass blows up call stack URL: https://github.com/apache/incubator-tvm/issues/4534#issuecomment-594489051 @YunLexi : The actual issue in dead code elimination pass is fixed

[GitHub] [incubator-tvm] masahi merged pull request #4982: [Torch] fix unordered dictionary problem for python version under 3.6

masahi merged pull request #4982: [Torch] fix unordered dictionary problem for python version under 3.6 URL: https://github.com/apache/incubator-tvm/pull/4982 This is an automated message from the Apache Git Service. To

[GitHub] [incubator-tvm] inadob commented on issue #4926: [TFLITE][FRONTEND]Reduce_any op parsing support

inadob commented on issue #4926: [TFLITE][FRONTEND]Reduce_any op parsing support URL: https://github.com/apache/incubator-tvm/pull/4926#issuecomment-594419573 LGTM This is an automated message from the Apache Git Service. To

[incubator-tvm] branch master updated (98b1759 -> 5a0f39b)

This is an automated email from the ASF dual-hosted git repository. masahi pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from 98b1759 [Relay] Target annotation for external codegen (#4933) add 5a0f39b [Torch] fix unordered