[GitHub] [incubator-tvm] LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support

LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596175172 > CI's LLVM is LLVM 4.0. I think we should supply `quantized add` so that we avoid it is just a lucky. Just tested, it's

[GitHub] [incubator-tvm] sergei-grechanik commented on issue #1996: [RFC][WIP] Tensor Expression level automatic differentiation

sergei-grechanik commented on issue #1996: [RFC][WIP] Tensor Expression level automatic differentiation URL: https://github.com/apache/incubator-tvm/issues/1996#issuecomment-596172921 @MarisaKirisame What do you think about adding a scatter-like reduction to TVM's tensor expressions? (I me

[GitHub] [incubator-tvm] yzhliu commented on issue #5007: kill from tvm import te

yzhliu commented on issue #5007: kill from tvm import te URL: https://github.com/apache/incubator-tvm/pull/5007#issuecomment-596172118 @mjamroz Thanks and welcome! This is an automated message from the Apache Git Service. To r

[GitHub] [incubator-tvm] yzhliu merged pull request #5007: kill from tvm import te

yzhliu merged pull request #5007: kill from tvm import te URL: https://github.com/apache/incubator-tvm/pull/5007 This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and

[incubator-tvm] branch master updated: kill from tvm import te (#5007)

This is an automated email from the ASF dual-hosted git repository. liuyizhi 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 87faaf1 kill from tvm import te (#5007

[incubator-tvm] branch master updated (ba47786 -> cf0a7e2)

This is an automated email from the ASF dual-hosted git repository. zhic pushed a change to branch master in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git. from ba47786 Add BN support with run-time mean and variance calculation (#4990) add cf0a7e2 [FRONTEND][TENSOR

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

zhiics commented on issue #4980: [FRONTEND][TENSORFLOW] support multiply outputs URL: https://github.com/apache/incubator-tvm/pull/4980#issuecomment-596171896 Thanks @vv1133 @srkreddy1238 This is an automated message from the

[GitHub] [incubator-tvm] zhiics merged pull request #4980: [FRONTEND][TENSORFLOW] support multiply outputs

zhiics merged pull request #4980: [FRONTEND][TENSORFLOW] support multiply outputs URL: https://github.com/apache/incubator-tvm/pull/4980 This is an automated message from the Apache Git Service. To respond to the message, pl

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

FrozenGene commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596171397 > > I doubt it is because of different LLVM version. > > Do you know the default llvm version in ci test? I can have a try loca

[GitHub] [incubator-tvm] LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support

LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596168987 > I doubt it is because of different LLVM version. Do you know the default llvm version in ci test? I can have a try local

[GitHub] [incubator-tvm] lfengad commented on issue #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation

lfengad commented on issue #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation URL: https://github.com/apache/incubator-tvm/pull/4990#issuecomment-596166737 > Thanks @lfengad This is merged now. Thank you so much for your help! 😄

[GitHub] [incubator-tvm] FrozenGene commented on issue #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation

FrozenGene commented on issue #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation URL: https://github.com/apache/incubator-tvm/pull/4990#issuecomment-596166401 Thanks @lfengad This is merged now.

[incubator-tvm] branch master updated: Add BN support with run-time mean and variance calculation (#4990)

This is an automated email from the ASF dual-hosted git repository. zhaowu 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 ba47786 Add BN support with run-time mea

[GitHub] [incubator-tvm] FrozenGene merged pull request #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation

FrozenGene merged pull request #4990: [TF][Relay] BatchNorm support with run-time mean and variance calculation URL: https://github.com/apache/incubator-tvm/pull/4990 This is an automated message from the Apache Git Service.

[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-596163419 sure This is an automated message from the Apache Git Service. To respond

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

tqchen commented on issue #3934: [Runtime] MISRA-C compliant TVM runtime URL: https://github.com/apache/incubator-tvm/pull/3934#issuecomment-596162926 @liangfu would be great if you can try to update(use simple testing as in other all in one deployment that does not depend on mxnet) :) --

[GitHub] [incubator-tvm] hypercubestart closed pull request #4924: [WIP][Relay][fix] fix alpha_equal commutativity

hypercubestart closed pull request #4924: [WIP][Relay][fix] fix alpha_equal commutativity URL: https://github.com/apache/incubator-tvm/pull/4924 This is an automated message from the Apache Git Service. To respond to the mes

[GitHub] [incubator-tvm] eqy edited a comment on issue #5005: [WIP]TVM android camera demo

eqy edited a comment on issue #5005: [WIP]TVM android camera demo URL: https://github.com/apache/incubator-tvm/pull/5005#issuecomment-596155814 The warnings are performance related; they should not affect the correctness of the output. By a cherry-picked screenshot, I do mean one that do

[GitHub] [incubator-tvm] eqy edited a comment on issue #5005: [WIP]TVM android camera demo

eqy edited a comment on issue #5005: [WIP]TVM android camera demo URL: https://github.com/apache/incubator-tvm/pull/5005#issuecomment-596155814 The warnings are performance related; they should not affect the correctness of the output. By a cherry-picked screenshot, I do mean one that do

[GitHub] [incubator-tvm] eqy commented on issue #5005: [WIP]TVM android camera demo

eqy commented on issue #5005: [WIP]TVM android camera demo URL: https://github.com/apache/incubator-tvm/pull/5005#issuecomment-596155814 The warnings are performance related, they should not affect the correctness of the output. By a cherry-picked screenshot, I do mean one that does not

[GitHub] [incubator-tvm] mjamroz opened a new pull request #5007: kill from tvm import te

mjamroz opened a new pull request #5007: kill from tvm import te URL: https://github.com/apache/incubator-tvm/pull/5007 one line to run from_mxnet This is an automated message from the Apache Git Service. To respond to the mes

[GitHub] [incubator-tvm] yagnasrinath commented on issue #5005: [WIP]TVM android camera demo

yagnasrinath commented on issue #5005: [WIP]TVM android camera demo URL: https://github.com/apache/incubator-tvm/pull/5005#issuecomment-596143301 Also, I get the following warnings while building the model, I am new to tvm, and I am not sure if they are harmless, tried searching in the foru

[GitHub] [incubator-tvm] yagnasrinath commented on issue #5005: [WIP]TVM android camera demo

yagnasrinath commented on issue #5005: [WIP]TVM android camera demo URL: https://github.com/apache/incubator-tvm/pull/5005#issuecomment-596141620 > thanks for picking this up! CC @srkreddy1238 @PariksheetPinjari909 > > If you get the chance, could you update the screenshot

[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-596126498 Thanks against for pushing this PR through @pasqoc this work is hugely appreciated by the TVM community! -

[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-596126449 @liangfu I just merged @liangfu 's scala linter fix: https://github.com/apache/incubator-tvm/pull/4998 If @pasqo

[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_r389303551 ## File path: vta/python/vta/testing/util.py ## @@ -59,8 +59,8 @@ def run(run_func):

[GitHub] [incubator-tvm] tmoreau89 commented on issue #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle

tmoreau89 commented on issue #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle URL: https://github.com/apache/incubator-tvm/pull/4998#issuecomment-596125703 Thanks @liangfu, @vegaluisjose the PR has been merged!

[incubator-tvm] branch master updated: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle (#4998)

This is an automated email from the ASF dual-hosted git repository. moreau 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 6a36fb4 [VTA][Chisel] Change Scala Linte

[GitHub] [incubator-tvm] tmoreau89 merged pull request #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle

tmoreau89 merged pull request #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle URL: https://github.com/apache/incubator-tvm/pull/4998 This is an automated message from the Apache Git Service. To respond to the

[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_r389294713 ## File path: vta/src/de10nano/cma_api.h ## @@ -27,6 +27,8 @@ extern "C" { #endif +

[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_r389292372 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -88,34 +237,486 @@ set_in

[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_r389279439 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -88,34 +237,486 @@ set_in

[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-596110493 @liangfu, @tmoreau89, for the linter changes I thought we had decided to do them in a different PR. The linter line in Mak

[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_r389284600 ## File path: vta/python/vta/testing/util.py ## @@ -59,8 +59,8 @@ def run(run_func):

[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_r389282347 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -33,7 +33,156 @@ set_inst

[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_r389279439 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -88,34 +237,486 @@ set_in

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

zhiics commented on issue #4980: [FRONTEND][TENSORFLOW] support multiply outputs URL: https://github.com/apache/incubator-tvm/pull/4980#issuecomment-596106840 Please retrigger the ci This is an automated message from the Apach

[GitHub] [incubator-tvm] lsy643 opened a new pull request #5006: fix bug for slice and tile of relay's frontend for tensorflow

lsy643 opened a new pull request #5006: fix bug for slice and tile of relay's frontend for tensorflow URL: https://github.com/apache/incubator-tvm/pull/5006 Fix bugs of `def _slice` and `def _tile` in `relay.frontend.tensorflow.py` file. 1. For `def _slice`, the codes added is used

[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_r389246377 ## File path: vta/python/vta/testing/util.py ## @@ -59,8 +59,8 @@ def run(run_func):

[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_r389245691 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -88,34 +237,486 @@ set_i

[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_r389245910 ## File path: vta/hardware/intel/scripts/soc_system.tcl ## @@ -33,7 +33,156 @@ set_ins

[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_r389246425 ## File path: vta/src/de10nano/cma_api.h ## @@ -27,6 +27,8 @@ extern "C" { #endif

[GitHub] [incubator-tvm] FrozenGene edited a comment on issue #4828: [QNN][TFLite] TFLite rounding mode support

FrozenGene edited a comment on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596083786 > I'm fine with both choices. The pooling implementation doesn't affect any other test except for this bit-exact computation.

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

FrozenGene commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596083786 > I'm fine with both choices. The pooling implementation doesn't affect any other test except for this bit-exact computation. It can

[GitHub] [incubator-tvm] LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support

LiangHao151941 commented on issue #4828: [QNN][TFLite] TFLite rounding mode support URL: https://github.com/apache/incubator-tvm/pull/4828#issuecomment-596081314 > Do you think it will be good if you send a separate PR for pooling op? I think it is more like a bug of pooling op integer imp

[GitHub] [incubator-tvm] liangfu commented on issue #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle

liangfu commented on issue #4998: [VTA][Chisel] Change Scala Linter scalafmt => scalastyle URL: https://github.com/apache/incubator-tvm/pull/4998#issuecomment-596068024 I think it might related to #4901 , let me trigger the testing pipeline again. -