mdw-octoml commented on a change in pull request #7728:
URL: https://github.com/apache/tvm/pull/7728#discussion_r600146495
##
File path: docker/Dockerfile.ci_qemu
##
@@ -64,3 +64,7 @@ RUN bash /install/ubuntu_install_qemu.sh
COPY install/ubuntu_install_zephyr.sh
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 8131364 [ONNX] Onnx node tests (#7720)
8131364 is
jroesch merged pull request #7720:
URL: https://github.com/apache/tvm/pull/7720
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please
masahi commented on issue #7730:
URL: https://github.com/apache/tvm/issues/7730#issuecomment-805406456
I see, this is the same issue raised by @csullivan in
https://github.com/apache/tvm/pull/6616#pullrequestreview-501380546
What was the solution to this problem? @jwfromm @csullivan
comaniac opened a new issue #7730:
URL: https://github.com/apache/tvm/issues/7730
The PR #7348 before batch_matmul because batch_matmul already supported
implicitly broadcast. However, the CuBLAS implementation doesn't change
accordingly, which results in the failure of the following
junrushao1994 commented on issue #7729:
URL: https://github.com/apache/tvm/issues/7729#issuecomment-805398055
I had a fix for this last summer but it somehow got reverted by the recent
libbacktrace PR...I will submit a PR to fix it later this week. Thanks for
bringing it up!
--
This is
masahi commented on issue #7713:
URL: https://github.com/apache/tvm/issues/7713#issuecomment-805397022
What LLVM version are you using? The recent PR introduced this change
https://github.com/apache/tvm/pull/7617
--
This is an automated message from the Apache Git Service.
To respond to
areusch commented on pull request #7653:
URL: https://github.com/apache/tvm/pull/7653#issuecomment-805394924
@zhiics I've added Python backwards-compat. Please let me know if you think
this is adequate. If so, I think we are ready to merge.
--
This is an automated message from the
comaniac commented on a change in pull request #7642:
URL: https://github.com/apache/tvm/pull/7642#discussion_r600077966
##
File path: tutorials/get_started/tensor_expr_get_started.py
##
@@ -255,41 +340,39 @@
fadd1(a, b, c)
tvm.testing.assert_allclose(c.asnumpy(),
AndrewZhaoLuo commented on pull request #7722:
URL: https://github.com/apache/tvm/pull/7722#issuecomment-805391908
@masahi PTAL
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
comaniac opened a new issue #7729:
URL: https://github.com/apache/tvm/issues/7729
After apply the PR #7153, some of my models got stack overflow when running
some passes. IIUC, this is because the containers use LOG that occupies the
stack. @tkonolige could you help fix this issue?
electriclilies edited a comment on pull request #7710:
URL: https://github.com/apache/tvm/pull/7710#issuecomment-805370118
@tqchen @jroesch @mbrookhart @anijain2305 I put up an RFC, please take a
look:
electriclilies edited a comment on pull request #7710:
URL: https://github.com/apache/tvm/pull/7710#issuecomment-805370118
@tqchen @jroesch @mbroohart @anijain2305 I put up an RFC, please take a
look:
electriclilies commented on pull request #7710:
URL: https://github.com/apache/tvm/pull/7710#issuecomment-805370118
@tqchen @jroesch @anijain2305 I put up an RFC, please take a look:
zhiics commented on pull request #7653:
URL: https://github.com/apache/tvm/pull/7653#issuecomment-805361926
> @zhiics it's definitely a breaking change, i'm not opposed to the warning
or some other way to notify downstream users. I don't know if code or forum or
other is the best channel
masahi commented on pull request #7722:
URL: https://github.com/apache/tvm/pull/7722#issuecomment-805359158
You've got a merge issue, need to rebase.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
hogepodge commented on a change in pull request #7642:
URL: https://github.com/apache/tvm/pull/7642#discussion_r600034455
##
File path: tutorials/get_started/tensor_expr_get_started.py
##
@@ -302,18 +385,452 @@
fadd_cl(a, b, c)
electriclilies closed pull request #7474:
URL: https://github.com/apache/tvm/pull/7474
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service,
hogepodge commented on a change in pull request #7642:
URL: https://github.com/apache/tvm/pull/7642#discussion_r600033842
##
File path: tutorials/get_started/tensor_expr_get_started.py
##
@@ -255,41 +340,39 @@
fadd1(a, b, c)
tvm.testing.assert_allclose(c.asnumpy(),
hogepodge commented on a change in pull request #7643:
URL: https://github.com/apache/tvm/pull/7643#discussion_r600031303
##
File path: tutorials/get_started/autotvm_matmul.py
##
@@ -0,0 +1,377 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more
tqchen commented on pull request #7653:
URL: https://github.com/apache/tvm/pull/7653#issuecomment-805343734
Given we are pre-1.0 we can just do our best effort when backward compact is
possible but not necessary have to spend an extra mile of effort. may not hurt
to post a notice to forum
areusch opened a new pull request #7728:
URL: https://github.com/apache/tvm/pull/7728
This PR unblocks #7557 by adding `onnx` to the python packages usable in
ci-qemu.
Also as part of rebuilding the container, change the method by which we
install kitware apt keys to make it more
This is an automated email from the ASF dual-hosted git repository.
marisa pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 6f0a656 [FIX] Fix temporary allocation size in
MarisaKirisame merged pull request #7709:
URL: https://github.com/apache/tvm/pull/7709
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service,
areusch commented on issue #7590:
URL: https://github.com/apache/tvm/issues/7590#issuecomment-805175522
https://ci.tlcpack.ai/job/tvm/job/PR-7653/8/console on `node.aladdin.cuda0`
looks like it is stuck in xargs rm -f
in both cases:
`+ echo 'INFO:
areusch commented on pull request #7723:
URL: https://github.com/apache/tvm/pull/7723#issuecomment-805061932
thanks @mehrdadh !
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
areusch merged pull request #7723:
URL: https://github.com/apache/tvm/pull/7723
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new f88c2be [microTVM] Update nrfjprog on reference
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 8cbc1644f6c47beeba1c32022bb084be670f59f8
Merge: 87be5dd 37e6df1
Author: Andrew Reusch
AuthorDate: Tue Mar 23
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
discard 87798bf try bumping synr
new 87be5dd fix path
add e467748 [CPP_RPC] allow user supplied work
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 87be5dde40efe6743290ec9b26a7b2f2b7333eff
Author: Andrew Reusch
AuthorDate: Tue Mar 23 09:45:35 2021 -0700
mdw-octoml commented on a change in pull request #7723:
URL: https://github.com/apache/tvm/pull/7723#discussion_r599748630
##
File path: apps/microtvm/reference-vm/zephyr/base-box/test-config.json
##
@@ -1,4 +1,12 @@
-{"vid_hex": "0483",
- "pid_hex": "374b",
- "test_cmd":
areusch commented on a change in pull request #7723:
URL: https://github.com/apache/tvm/pull/7723#discussion_r599737747
##
File path: apps/microtvm/reference-vm/zephyr/base-box/test-config.json
##
@@ -1,4 +1,12 @@
-{"vid_hex": "0483",
- "pid_hex": "374b",
- "test_cmd":
tkonolige commented on issue #7705:
URL: https://github.com/apache/tvm/issues/7705#issuecomment-805048911
@xiebaiyuan Thanks for the extra information. It looks like the compiler is
different between libbacktrace and the rest of the cmake project. Can you try
this branch:
areusch commented on pull request #7653:
URL: https://github.com/apache/tvm/pull/7653#issuecomment-804961316
@zhiics it's definitely a breaking change, i'm not opposed to the warning or
some other way to notify downstream users. I don't know if code or forum or
other is the best channel
tqchen closed issue #7725:
URL: https://github.com/apache/tvm/issues/7725
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact
tqchen commented on issue #7725:
URL: https://github.com/apache/tvm/issues/7725#issuecomment-804933904
Thanks @xiebaiyuan please open a new thread on
https://discuss.tvm.apache.org/ We generally use the discuss forum for related
questions
--
This is an automated message from the Apache
tqchen commented on pull request #7721:
URL: https://github.com/apache/tvm/pull/7721#issuecomment-804922459
@icemelon9 please rebase against the main
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to
tqchen commented on issue #7727:
URL: https://github.com/apache/tvm/issues/7727#issuecomment-804912236
helloe @majercakdavid , yes it is possible via emscripten polyfill version
of wasi. Please see
https://github.com/apache/tvm/tree/main/web#run-wasm-remotely-through-websocket-rpc
tqchen closed issue #7727:
URL: https://github.com/apache/tvm/issues/7727
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please contact
tqchen commented on pull request #7714:
URL: https://github.com/apache/tvm/pull/7714#issuecomment-804910681
Thanks @echuraev
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 37e6df1 [METAL] Fix memory leaks in Metal runtime
tqchen merged pull request #7714:
URL: https://github.com/apache/tvm/pull/7714
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please
majercakdavid opened a new issue #7727:
URL: https://github.com/apache/tvm/issues/7727
Hello,
please is it possible and if how to use the WASM models in the browser on
the client side? The problem is that the wasi runtime requires "fs" module to
work, which is unavailable on the
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new f09f02e [TORCH] Implement avg_pool1d (#7694)
f09f02e
masahi commented on pull request #7694:
URL: https://github.com/apache/tvm/pull/7694#issuecomment-804733311
Thanks @cgerum
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
masahi merged pull request #7694:
URL: https://github.com/apache/tvm/pull/7694
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please
hebowen325 commented on issue #7660:
URL: https://github.com/apache/tvm/issues/7660#issuecomment-804691495
@nhynes I find that issues about sgx in tvm were mostly solved by you, could
you help me? I would be very grateful indeed for any help you could give me.
--
This is an automated
comaniac commented on pull request #7162:
URL: https://github.com/apache/tvm/pull/7162#issuecomment-804679951
Gentle ping @lsy643
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific
comaniac commented on pull request #7665:
URL: https://github.com/apache/tvm/pull/7665#issuecomment-804677134
Thanks @jtuyls @tkonolige
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the
This is an automated email from the ASF dual-hosted git repository.
comaniac pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 4c66fb2 Fix GraphModule.load_params to allow
comaniac merged pull request #7665:
URL: https://github.com/apache/tvm/pull/7665
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
For queries about this service, please
comaniac commented on pull request #7698:
URL: https://github.com/apache/tvm/pull/7698#issuecomment-804674880
Just a guess. Is that due to circular dependency?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
comaniac commented on pull request #7564:
URL: https://github.com/apache/tvm/pull/7564#issuecomment-804670541
> We did explore using the same fix as for Ethos-N (giving a 'null'
ConstantUpdater), but this doesn't work for ACL as ACL does load the constants
from MetadataModule. Ethos-N
neoming opened a new issue #7726:
URL: https://github.com/apache/tvm/issues/7726
I follow this tutorial:
[bitstream-generation-with-xilinx-toolchains](https://tvm.apache.org/docs/vta/install.html#bitstream-generation-with-xilinx-toolchains)
I change the `vivado.tcl` file
from
zhiics commented on pull request #7653:
URL: https://github.com/apache/tvm/pull/7653#issuecomment-804657364
@areusch yeah, warning may not be needed. I was just trying to make sure
that we don't break all the downstream deployment by letting them know that
what is going to happen there.
zhiics edited a comment on pull request #7564:
URL: https://github.com/apache/tvm/pull/7564#issuecomment-804654019
The approach I was thinking is that we can probably use the `MetadataModule`
as the only place to save the weights. Other modules including
`GraphRuntimeModule` can directly
zhiics commented on pull request #7564:
URL: https://github.com/apache/tvm/pull/7564#issuecomment-804654019
The approach I was thinking is that we can probably use the `MetadataModule`
as the only place to save the weights. Other modules including
`GraphRuntimeModule` can directly query
58 matches
Mail list logo
