PhilippvK commented on pull request #9256:
URL: https://github.com/apache/tvm/pull/9256#issuecomment-943046720
@masahi I first tried to follow the same approach as in the PyTorch
frontend, just passing a dict to overwrite the convert map. However in the
TFLite frontend, the `convert_*` fun
zhaiyi000 commented on issue #9268:
URL: https://github.com/apache/tvm/issues/9268#issuecomment-943021024
I still get an error when testing on the iOS sumulator, but it is not the
same as the above error, prompting `unsupported case in deploy.dylib`
```
(py38) zy@diyideMacBook-Pro
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 7e014a4 [ONNX] [Relay] Resize Opset 13 (#9265)
add 575ac86 Skip onnx test cases if no onnx (#9272)
No new revision
masahi merged pull request #9272:
URL: https://github.com/apache/tvm/pull/9272
--
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.
To unsubscribe, e-mail: commits-unsubscr...
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 523eb12 [Pytest] Sort unit tests before running. (#9188)
add 7e014a4 [ONNX] [Relay] Resize Opset 13 (#9265)
No new
masahi merged pull request #9265:
URL: https://github.com/apache/tvm/pull/9265
--
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.
To unsubscribe, e-mail: commits-unsubscr...
masahi commented on pull request #9256:
URL: https://github.com/apache/tvm/pull/9256#issuecomment-942983163
Yeah PyTorch frontend also has something similar
https://github.com/apache/tvm/blob/2b57907d9ed9b6c31e368ef9b517e528dff3ae9e/python/tvm/relay/frontend/pytorch.py#L3288-L3289.
I think
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 523eb12 [Pytest] Sort unit tests before running. (#91
areusch merged pull request #9188:
URL: https://github.com/apache/tvm/pull/9188
--
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.
To unsubscribe, e-mail: commits-unsubscr..
areusch commented on pull request #9254:
URL: https://github.com/apache/tvm/pull/9254#issuecomment-942934083
thanks for the quick fix @mousius
--
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
areusch commented on pull request #9256:
URL: https://github.com/apache/tvm/pull/9256#issuecomment-942933735
@philippvk can you retrigger the CI?
@jwfromm @masahi are you able to help review this PR?
--
This is an automated message from the Apache Git Service.
To respond to the mes
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 4c00264 [CI] Pre-build Reference System Dependencies
areusch commented on pull request #9270:
URL: https://github.com/apache/tvm/pull/9270#issuecomment-942931703
thanks @mousius, the PR is now merged!
--
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 t
areusch merged pull request #9270:
URL: https://github.com/apache/tvm/pull/9270
--
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.
To unsubscribe, e-mail: commits-unsubscr..
areusch commented on a change in pull request #9255:
URL: https://github.com/apache/tvm/pull/9255#discussion_r728621033
##
File path: src/runtime/crt/crt_config-template.h
##
@@ -49,7 +49,10 @@
#define TVM_CRT_MAX_STRLEN_DLTYPE 10
/*! Maximum supported string length in func
areusch commented on issue #8953:
URL: https://github.com/apache/tvm/issues/8953#issuecomment-942929570
@philippvk following up on the PR
--
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 spec
areusch commented on pull request #9273:
URL: https://github.com/apache/tvm/pull/9273#issuecomment-942918249
https://ci.tlcpack.ai/blue/organizations/jenkins/tvm/detail/ci-docker-staging/165/pipeline/
--
This is an automated message from the Apache Git Service.
To respond to the message,
areusch commented on pull request #9273:
URL: https://github.com/apache/tvm/pull/9273#issuecomment-942918101
i think the error was due to missing PR 9227 but just rerunning once more to
check
--
This is an automated message from the Apache Git Service.
To respond to the message, please l
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 e45ccbb5126104befc425410eb490fa7771ed73f
Author: Andrew Reusch
AuthorDate: Wed Oct 13 07:59:38 2021 -0700
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.
omit 55aa699 Bump ci-gpu to v0.78.
add 76aa3c8 [UnitTest] Removed vulkan from CI run of task_python_topi.s
masahi edited a comment on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942895664
I think it is reasonable to ask users for an estimate of a range of
dynamism. Without such estimate, or if the estimate turns out to be off, we
just fallback to a default kern
masahi edited a comment on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942895664
I think it is reasonable to ask users for an estimate of a range of
dynamism. Without such estimate, or if the estimate turns out to be off, we
just fallback to a default kern
masahi commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942895664
I think it is reasonable to ask users for an estimate of a range of
dynamism. Without such estimate, we just fallback to a default kernel that
works on any input shapes, which should
huajsj opened a new pull request #9279:
URL: https://github.com/apache/tvm/pull/9279
Issue:
Some bash code in this tutorial does not get syntax highlighting because
of the format errors.
Solution:
Fix the 'sphinx' 'rst' style error.
--
This is an automated message
laolihaile commented on issue #6895:
URL: https://github.com/apache/tvm/issues/6895#issuecomment-942882073
I have the same problem, how can I solve it?There is no corresponding
solution on the https://discuss.tvm.apache.org/
--
This is an automated message from the Apache Git Service.
To
comaniac commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942878845
Right. Probably just need some experiments to see how many kernels should be
generated to cover a range of batch sizes, and we may just hardcore the
dispatching logic first to make
masahi commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942877261
> I agree that kernel picking should be handled by the custom runtime.
It would be interesting if we can apply the same logic that AutoTIR would
develop soon, since they need t
zhiics commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942853797
> > At this moment, CUTLASS does not provide heuristics to choose which
kernel to use based on the runtime information. The user of CUTLASS needs to
make the decision to pick kernels
vinx13 commented on a change in pull request #9224:
URL: https://github.com/apache/tvm/pull/9224#discussion_r728546565
##
File path: tests/python/unittest/test_tvmscript_ops.py
##
@@ -101,5 +101,65 @@ def test_get_valid_counts_script_func():
_check_get_valid_counts_with_nu
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/tvm.git.
from 2dc58be Bumping up CMSIS-NN version to be in sync with TFLu (#9247)
add b206570 [Runtime] Pipeline Executor Second
masahi merged pull request #9108:
URL: https://github.com/apache/tvm/pull/9108
--
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.
To unsubscribe, e-mail: commits-unsubscr...
masahi commented on pull request #9108:
URL: https://github.com/apache/tvm/pull/9108#issuecomment-942829812
thanks @huajsj @comaniac
--
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
masahi commented on a change in pull request #9223:
URL: https://github.com/apache/tvm/pull/9223#discussion_r728534141
##
File path: src/target/llvm/llvm_common.cc
##
@@ -139,8 +152,22 @@ std::unique_ptr
GetLLVMTargetMachine(const Target& target,
ICHECK(allow_null) << err
masahi commented on a change in pull request #9223:
URL: https://github.com/apache/tvm/pull/9223#discussion_r728534141
##
File path: src/target/llvm/llvm_common.cc
##
@@ -139,8 +152,22 @@ std::unique_ptr
GetLLVMTargetMachine(const Target& target,
ICHECK(allow_null) << err
masahi commented on a change in pull request #9223:
URL: https://github.com/apache/tvm/pull/9223#discussion_r728532649
##
File path: src/target/llvm/llvm_common.cc
##
@@ -106,10 +106,23 @@ void ParseLLVMTargetOptions(const Target& target,
std::string* triple, std::stri
#if TV
areusch commented on pull request #9277:
URL: https://github.com/apache/tvm/pull/9277#issuecomment-942773297
@tkonolige also mentioned we need to double-check if DLDevice can be sent
over RPC properly.
--
This is an automated message from the Apache Git Service.
To respond to the message
tkonolige commented on pull request #9275:
URL: https://github.com/apache/tvm/pull/9275#issuecomment-942773268
There's no guarantee of ordering of columns in the csv, either we need to
add ordering or make the test order them.
--
This is an automated message from the Apache Git Service.
mbs-octoml commented on pull request #9012:
URL: https://github.com/apache/tvm/pull/9012#issuecomment-942772889
@linlifan you're quite right, sorry. https://github.com/apache/tvm/pull/9278.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log
mbs-octoml opened a new pull request #9278:
URL: https://github.com/apache/tvm/pull/9278
Forgot to do this when I switched to VLOG, sorry.
(CORE-97)
--
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
tkonolige commented on a change in pull request #9277:
URL: https://github.com/apache/tvm/pull/9277#discussion_r728492109
##
File path: python/tvm/contrib/graph_executor.py
##
@@ -98,17 +98,17 @@ def get_device(libmod, device):
device_type_id = []
for cur_dev in devic
mehrdadh commented on a change in pull request #9229:
URL: https://github.com/apache/tvm/pull/9229#discussion_r728480988
##
File path: python/tvm/driver/tvmc/common.py
##
@@ -520,3 +522,84 @@ def parse_configs(input_configs):
pass_context_configs[name] = parsed_value
areusch opened a new pull request #9277:
URL: https://github.com/apache/tvm/pull/9277
* Fix GraphExecutor factory instantiation.
This PR leverages DLDevice support in PackedFunc to improve the
GraphExecutor parameter-passing style between Python and c++.
--
This is an automated m
areusch opened a new pull request #9276:
URL: https://github.com/apache/tvm/pull/9276
Cleaning up test_link_params to support the new parameterized testing.
cc @Lunderberg
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitH
AndrewZhaoLuo commented on pull request #9252:
URL: https://github.com/apache/tvm/pull/9252#issuecomment-942740031
Performance is extremely bad, with pretty much every model I have having
final inference regressions in the range of 60%. I'm going to close this for
now, but might investigat
AndrewZhaoLuo closed pull request #9252:
URL: https://github.com/apache/tvm/pull/9252
--
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.
To unsubscribe, e-mail: commits-unsu
vinx13 commented on issue #9268:
URL: https://github.com/apache/tvm/issues/9268#issuecomment-942693061
cc @apeskov
--
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.
To unsu
areusch commented on pull request #9225:
URL: https://github.com/apache/tvm/pull/9225#issuecomment-942460738
also it's worth pointing out that we would avoid merging incremental name
cleanups in the future (as this would invalidate autotuning logs), but since
Cortex-M autotuning is still g
areusch commented on pull request #9270:
URL: https://github.com/apache/tvm/pull/9270#issuecomment-942520731
@Mousius do you have an idea how much larger this makes ci-cpu? just wary of
including build artifacts in our docker base images
--
This is an automated message from the Apache Gi
shingjan commented on pull request #9224:
URL: https://github.com/apache/tvm/pull/9224#issuecomment-942589018
@vinx13 With
https://github.com/apache/tvm/blob/main/src/te/operation/create_primfunc.cc#L105-L109
removed, all tests under `test_te_*` passed. Should be good to merge after the
c
Mousius edited a comment on pull request #9270:
URL: https://github.com/apache/tvm/pull/9270#issuecomment-942544509
@areusch the Driver is about 364K and CMSIS NN is about 1.6MB
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub
mehrdadh commented on pull request #9274:
URL: https://github.com/apache/tvm/pull/9274#issuecomment-942572704
cc @areusch @gromero @guberti
--
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 s
hogepodge commented on issue #9217:
URL: https://github.com/apache/tvm/issues/9217#issuecomment-942479259
It looks like the cargo build in the `task_python_docs.sh` script was
disabled. Links to PR and issue:
https://github.com/apache/tvm/pull/7743
https://github.com/apache/tvm/is
areusch merged pull request #9225:
URL: https://github.com/apache/tvm/pull/9225
--
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.
To unsubscribe, e-mail: commits-unsubscr..
electriclilies commented on pull request #9251:
URL: https://github.com/apache/tvm/pull/9251#issuecomment-942584558
Thanks all!
--
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 comme
areusch commented on issue #9085:
URL: https://github.com/apache/tvm/issues/9085#issuecomment-942396843
```
docker pull tlcpackstaging/ci_gpu:20210929-225912-da5b4fbfe-validated
docker tag tlcpackstaging/ci_gpu:20210929-225912-da5b4fbfe-validated
tlcpack/ci-gpu:v0.78
docker push tl
Lunderberg opened a new pull request #9275:
URL: https://github.com/apache/tvm/pull/9275
`str(report)` calls `ReportNode::AsTable()`, which includes aggregate
values. Otherwise negligible differences in the computed value can be rounded
differently after the round trip. This was first [n
areusch commented on a change in pull request #9074:
URL: https://github.com/apache/tvm/pull/9074#discussion_r728244569
##
File path: python/tvm/driver/tvmc/frontends.py
##
@@ -88,10 +96,54 @@ def import_keras():
from tensorflow import keras
return tf, keras
CircleSpin commented on a change in pull request #9265:
URL: https://github.com/apache/tvm/pull/9265#discussion_r728242091
##
File path: python/tvm/relay/frontend/onnx.py
##
@@ -2697,6 +2697,40 @@ def _impl_v10(cls, inputs, attr, params):
@classmethod
def _impl_v11(
mikepapadim commented on pull request #9103:
URL: https://github.com/apache/tvm/pull/9103#issuecomment-942512206
@mbs-octoml @jroesch @tqchen this can be merged now
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use
mbrookhart commented on pull request #9248:
URL: https://github.com/apache/tvm/pull/9248#issuecomment-942446645
Thanks @rkimball @comaniac
--
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 sp
areusch merged pull request #9247:
URL: https://github.com/apache/tvm/pull/9247
--
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.
To unsubscribe, e-mail: commits-unsubscr..
hwu36 commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942558026
> I assume they also generate a run time dispatching logic (also in the
generated C source code) to determine which kernel should be used given the
known shape in run time.
At
mehrdadh commented on pull request #9225:
URL: https://github.com/apache/tvm/pull/9225#issuecomment-942469917
@areusch I agree that we should come up with a naming system at least for
microTVM at the moment if not possible for all schedules. I suggest we settle
down on something before mer
Mousius commented on pull request #9270:
URL: https://github.com/apache/tvm/pull/9270#issuecomment-942544509
--
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.
To unsubscribe,
mbrookhart merged pull request #9248:
URL: https://github.com/apache/tvm/pull/9248
--
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.
To unsubscribe, e-mail: commits-unsubsc
areusch commented on issue #9217:
URL: https://github.com/apache/tvm/issues/9217#issuecomment-942464477
cc @jroesch do you know how we generate rust docs?
--
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
AndrewZhaoLuo commented on a change in pull request #9184:
URL: https://github.com/apache/tvm/pull/9184#discussion_r727574893
##
File path: python/tvm/topi/searchsorted.py
##
@@ -0,0 +1,121 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or more contributor
emijiayw commented on a change in pull request #9265:
URL: https://github.com/apache/tvm/pull/9265#discussion_r727677663
##
File path: python/tvm/relay/frontend/onnx.py
##
@@ -2697,6 +2697,40 @@ def _impl_v10(cls, inputs, attr, params):
@classmethod
def _impl_v11(cl
rkimball commented on a change in pull request #9248:
URL: https://github.com/apache/tvm/pull/9248#discussion_r727253356
##
File path: tests/python/unittest/test_autotvm_graph_tuner_utils.py
##
@@ -155,6 +158,19 @@ def test_get_out_nodes():
)
+@pytest.mark.parametr
huajsj commented on a change in pull request #9243:
URL: https://github.com/apache/tvm/pull/9243#discussion_r727681973
##
File path: python/tvm/runtime/module.py
##
@@ -185,6 +185,11 @@ def type_key(self):
"""Get type key of the module."""
return _ffi_api.Modu
KJlaccHoeUM9l commented on pull request #9212:
URL: https://github.com/apache/tvm/pull/9212#issuecomment-942272506
@areusch, @jwfromm
Could you review this PR?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
UR
shingjan commented on a change in pull request #9224:
URL: https://github.com/apache/tvm/pull/9224#discussion_r727431386
##
File path: tests/python/unittest/test_tvmscript_complete.py
##
@@ -272,10 +272,30 @@ def test_complete_match_buffer():
tvm.ir.assert_structural_equal
areusch closed pull request #8892:
URL: https://github.com/apache/tvm/pull/8892
--
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.
To unsubscribe, e-mail: commits-unsubscr..
areusch commented on pull request #8892:
URL: https://github.com/apache/tvm/pull/8892#issuecomment-941525577
@mbs-octoml seems you are taking this on so i will close this PR. @jroesch
can feel free to reopen if he has cycles to push it through.
--
This is an automated message from the Ap
comaniac commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942064270
--
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.
To unsubscribe
mbs-octoml commented on a change in pull request #9246:
URL: https://github.com/apache/tvm/pull/9246#discussion_r727383049
##
File path: include/tvm/relay/executor.h
##
@@ -0,0 +1,276 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contributor
zhaiyi000 commented on issue #9268:
URL: https://github.com/apache/tvm/issues/9268#issuecomment-942355025
I tested it on iphone7 (ios13.7) and it still has the same problem
When I compiled `tvm_runtime`, I specified `DCMAKE_SYSTEM_VERSION=13.0` and
`DCMAKE_OSX_DEPLOYMENT_TARGET=13.0`
tmoreau89 merged pull request #9198:
URL: https://github.com/apache/tvm/pull/9198
--
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.
To unsubscribe, e-mail: commits-unsubscr
masahi commented on a change in pull request #9184:
URL: https://github.com/apache/tvm/pull/9184#discussion_r727476180
##
File path: include/tvm/relay/attrs/algorithm.h
##
@@ -76,6 +76,19 @@ struct TopKAttrs : public tvm::AttrsNode {
}
};
+struct SearchSortedAttrs : publi
Lunderberg commented on pull request #9188:
URL: https://github.com/apache/tvm/pull/9188#issuecomment-941162714
Rebased on main, because it looks like the CI is stalling out a bit on
vulkan+topi tests that were unintentionally enabled in
https://github.com/apache/tvm/pull/9093, then intent
zhaiyi000 closed issue #8545:
URL: https://github.com/apache/tvm/issues/8545
--
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.
To unsubscribe, e-mail: commits-unsubscr...@t
junrushao1994 commented on a change in pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#discussion_r727471035
##
File path: .gitmodules
##
@@ -13,3 +13,6 @@
[submodule "3rdparty/libbacktrace"]
path = 3rdparty/libbacktrace
url = https://github.co
junrushao1994 commented on pull request #9263:
URL: https://github.com/apache/tvm/pull/9263#issuecomment-941577021
CC: @Hzfengsy @comaniac
--
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 sp
junrushao1994 commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-941462765
Really cool work @Laurawly!
--
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
leandron commented on pull request #9218:
URL: https://github.com/apache/tvm/pull/9218#issuecomment-941858425
Thanks @Mousius @areusch
--
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 specif
areusch merged pull request #28:
URL: https://github.com/apache/tvm-rfcs/pull/28
--
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.
To unsubscribe, e-mail: commits-unsubscr.
areusch merged pull request #9159:
URL: https://github.com/apache/tvm/pull/9159
--
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.
To unsubscribe, e-mail: commits-unsubscr..
masahi commented on a change in pull request #9108:
URL: https://github.com/apache/tvm/pull/9108#discussion_r727593939
##
File path: src/runtime/pipeline/pipeline_struct.h
##
@@ -0,0 +1,185 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or more contri
areusch commented on pull request #34:
URL: https://github.com/apache/tvm-rfcs/pull/34#issuecomment-941462554
@mbs-octoml @electriclillies and I discussed this at length and we followed
up with @Mousius offline as well. While it is tempting to re-use
`resource_handle` to pass a `this` cont
areusch commented on a change in pull request #9218:
URL: https://github.com/apache/tvm/pull/9218#discussion_r727372392
##
File path: python/tvm/driver/tvmc/target.py
##
@@ -0,0 +1,74 @@
+# Licensed to the Apache Software Foundation (ASF) under one
Review comment:
shoul
areusch commented on a change in pull request #9229:
URL: https://github.com/apache/tvm/pull/9229#discussion_r727495939
##
File path: apps/microtvm/zephyr/template_project/microtvm_api_server.py
##
@@ -229,40 +229,69 @@ def _get_nrf_device_args(options):
PROJECT_OPTIONS = [
masahi edited a comment on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-941990346
--
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.
To unsubs
zhiics commented on pull request #9261:
URL: https://github.com/apache/tvm/pull/9261#issuecomment-942200090
I think even C source code should be able to handle dynamic shapes as well
since it only expects tensors at the runtime, or I might forget something here.
But in general, json format
junrushao1994 edited a comment on pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#issuecomment-941683513
--
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.
To
areusch commented on pull request #7919:
URL: https://github.com/apache/tvm/pull/7919#issuecomment-941674880
@junrushao1994 just curious what the motivation is behind your question?
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to Gi
vinx13 merged pull request #9262:
URL: https://github.com/apache/tvm/pull/9262
--
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.
To unsubscribe, e-mail: commits-unsubscr...
areusch commented on a change in pull request #28:
URL: https://github.com/apache/tvm-rfcs/pull/28#discussion_r727367147
##
File path: rfcs/0028-command-line-registry-composition.md
##
@@ -0,0 +1,153 @@
+- Feature Name: Command Line Composition from Internal Registry
+- Start D
kparzysz-quic merged pull request #9220:
URL: https://github.com/apache/tvm/pull/9220
--
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.
To unsubscribe, e-mail: commits-unsu
vinx13 commented on pull request #9224:
URL: https://github.com/apache/tvm/pull/9224#issuecomment-941277329
--
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.
To unsubscribe,
comaniac commented on a change in pull request #9248:
URL: https://github.com/apache/tvm/pull/9248#discussion_r727311387
##
File path: python/tvm/autotvm/graph_tuner/utils/traverse_graph.py
##
@@ -50,6 +51,8 @@ def expr2graph(expr, target_ops, node_dict, node_list):
Ea
1 - 100 of 172 matches
Mail list logo