This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 08b08b1 [TFLite] Fix detection of crop in convert_batch_to_space_nd
(#6670)
add 4c4d3dc Fix tutorial
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 08b08b1 [TFLite] Fix detection of crop in convert_batch_to_space_nd
(#6670)
add 4c4d3dc Fix tutorial
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 08b08b1 [TFLite] Fix detection of crop in convert_batch_to_space_nd
(#6670)
add 4c4d3dc Fix tutorial
This is an automated email from the ASF dual-hosted git repository.
moreau pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git
The following commit(s) were added to refs/heads/main by this push:
new 4c4d3dc Fix tutorial broken by Docker build
tmoreau89 merged pull request #6694:
URL: https://github.com/apache/incubator-tvm/pull/6694
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
masahi commented on pull request #6602:
URL: https://github.com/apache/incubator-tvm/pull/6602#issuecomment-709702663
thanks @siju-samuel
I added `pytorch_utils.py` and moved the version check function there
This is an
Beya2019 commented on pull request #6516:
URL: https://github.com/apache/incubator-tvm/pull/6516#issuecomment-709700238
Hi @yzhliu, can you help to have a look at this submit? Thanks very much.
This is an automated message
siju-samuel commented on pull request #6670:
URL: https://github.com/apache/incubator-tvm/pull/6670#issuecomment-709695528
Thanks @trevor-m @anijain2305. This PR is merged.
This is an automated message from the Apache Git
lixiaoquan opened a new pull request #6695:
URL: https://github.com/apache/incubator-tvm/pull/6695
@mbrookhart Could you please take a look?
This is an automated message from the Apache Git Service.
To respond to the
This is an automated email from the ASF dual-hosted git repository.
sijusamuel pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 8243145 [FIX,MICROTVM] Skip microtvm tests if microtvm is not built
(#6693)
add 08b08b1 [TFLite]
siju-samuel merged pull request #6670:
URL: https://github.com/apache/incubator-tvm/pull/6670
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
siju-samuel commented on a change in pull request #6602:
URL: https://github.com/apache/incubator-tvm/pull/6602#discussion_r505998308
##
File path: python/tvm/relay/frontend/qnn_torch.py
##
@@ -26,6 +26,14 @@
from tvm.relay import op as _op
from tvm.relay.frontend.common
siju-samuel commented on a change in pull request #6685:
URL: https://github.com/apache/incubator-tvm/pull/6685#discussion_r505991920
##
File path: python/tvm/relay/frontend/tensorflow.py
##
@@ -890,6 +890,44 @@ def _impl(inputs, attr, params, mod):
return _impl
+def
siju-samuel commented on a change in pull request #6685:
URL: https://github.com/apache/incubator-tvm/pull/6685#discussion_r505991645
##
File path: python/tvm/relay/frontend/tensorflow.py
##
@@ -890,6 +890,44 @@ def _impl(inputs, attr, params, mod):
return _impl
+def
jroesch commented on pull request #6685:
URL: https://github.com/apache/incubator-tvm/pull/6685#issuecomment-709673851
cc @tkonolige
This is an automated message from the Apache Git Service.
To respond to the message,
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 3e8ba2a [Docker] Update CI CPU and GPU images based on new Docker
build files. (#6690)
add 8243145
tqchen merged pull request #6693:
URL: https://github.com/apache/incubator-tvm/pull/6693
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
jroesch opened a new pull request #6694:
URL: https://github.com/apache/incubator-tvm/pull/6694
cc @tqchen @tmoreau89 this change is required for CI to pass on the new
images.
This is an automated message from the Apache
This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from b121278 int32 pooling with int64 shapes (#6687)
add 3e8ba2a [Docker] Update CI CPU and GPU images based
jroesch merged pull request #6690:
URL: https://github.com/apache/incubator-tvm/pull/6690
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 edited a comment on pull request #6692:
URL: https://github.com/apache/incubator-tvm/pull/6692#issuecomment-709642068
In this particular case, ICHECK perhaps should not end up in ir/diagnostic,
but instead in `support/logging.h`, moving the marco defs there would be the
simplest
tqchen commented on pull request #6692:
URL: https://github.com/apache/incubator-tvm/pull/6692#issuecomment-709642068
In this particular case, ICHECK perhaps should not end up in ir/diagnostic,
but instead in `support/logging.h`, moving the marco defs there would be the
simplest solution
tkonolige opened a new pull request #6693:
URL: https://github.com/apache/incubator-tvm/pull/6693
This is a simple PR that adds `@tvm.testing.requires_micro` for microtvm
tests. Previously, if microtvm was not built, no tests would be run.
@areusch
masahi commented on pull request #6602:
URL: https://github.com/apache/incubator-tvm/pull/6602#issuecomment-709602965
@siju-samuel @anijain2305 can you merge this? It is a prereq for upgrading
our CI to the latest pytorch version
jroesch commented on a change in pull request #6692:
URL: https://github.com/apache/incubator-tvm/pull/6692#discussion_r505858000
##
File path: include/tvm/ir/diagnostic_context.h
##
@@ -0,0 +1,222 @@
+/*
+ * Licensed to the Apache Software Foundation (ASF) under one
+ * or
tqchen commented on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-709583351
Thanks @trevor-m cc @hzfan Given that those are constant shapes, we should
expect NarrowDataTypes to narrow dtypes to i32, it would be great to look into
the IR those kernels
rkimball opened a new pull request #6692:
URL: https://github.com/apache/incubator-tvm/pull/6692
There were circular dependencies in object.h which made use of ICHECK in
Object problematic.
This is an automated message from
trevor-m commented on issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691#issuecomment-709569953
FYI @kevinthesun @hzfan @zhiics @tqchen
This is an automated message from the Apache Git Service.
To respond
trevor-m opened a new issue #6691:
URL: https://github.com/apache/incubator-tvm/issues/6691
I've started noticing a large performance regression affecting Keras
MobileNetV2 caused by `INDEX_DEFAULT_I64=ON` (PR #6143). This is on an AWS
m5.12xlarge instance.
INDEX_DEFAULT_I64 |
comaniac commented on a change in pull request #6686:
URL: https://github.com/apache/incubator-tvm/pull/6686#discussion_r505784167
##
File path: src/te/schedule/schedule_dataflow_rewrite.cc
##
@@ -138,6 +138,15 @@ Tensor Schedule::cache_read(const Tensor& tensor, const
comaniac commented on a change in pull request #6686:
URL: https://github.com/apache/incubator-tvm/pull/6686#discussion_r505784167
##
File path: src/te/schedule/schedule_dataflow_rewrite.cc
##
@@ -138,6 +138,15 @@ Tensor Schedule::cache_read(const Tensor& tensor, const
jroesch commented on pull request #6690:
URL: https://github.com/apache/incubator-tvm/pull/6690#issuecomment-709535200
cc @tmoreau89 @tqchen @u99127 this should include all the newest changes.
This is an automated message
jroesch opened a new pull request #6690:
URL: https://github.com/apache/incubator-tvm/pull/6690
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL
trevor-m commented on pull request #6143:
URL: https://github.com/apache/incubator-tvm/pull/6143#issuecomment-709515877
FYI, I found that Keras MobileNetV2 model experiences a heavy perf
regression with i64 indices enabled.
With ON: 66.55801918395055 FPS
With OFF: 435.48951121558594
trevor-m edited a comment on pull request #6143:
URL: https://github.com/apache/incubator-tvm/pull/6143#issuecomment-709515877
@hzfan FYI, I found that Keras MobileNetV2 model experiences a heavy perf
regression with i64 indices enabled.
With ON: 66.55801918395055 FPS
With OFF:
anijain2305 commented on pull request #6670:
URL: https://github.com/apache/incubator-tvm/pull/6670#issuecomment-709502703
@siju-samuel Can you PTAL
This is an automated message from the Apache Git Service.
To respond to
anijain2305 commented on pull request #6670:
URL: https://github.com/apache/incubator-tvm/pull/6670#issuecomment-709502035
Saw this issue a couple of months ago. This looks good. Thanks Trevor!
This is an automated message
comaniac commented on pull request #6686:
URL: https://github.com/apache/incubator-tvm/pull/6686#issuecomment-709412464
The failed case in CI seems related to #6417
This is an automated message from the Apache Git Service.
masahi commented on issue #6689:
URL: https://github.com/apache/incubator-tvm/issues/6689#issuecomment-709392455
cc @yongwww
This is an automated message from the Apache Git Service.
To respond to the message, please log on
flip1995 commented on issue #4272:
URL: https://github.com/apache/incubator-tvm/issues/4272#issuecomment-709342481
Or to be more precise, you have to load your model like this:
```python
import ctypes
import tvm
from tvm.contrib import graph_runtime as runtime
flip1995 commented on issue #4272:
URL: https://github.com/apache/incubator-tvm/issues/4272#issuecomment-709335331
Oh damn, I totally forgot about it. Basically you have to add those two
lines to your python script, that runs your model on the PYNQ:
```python
dll_path =
tqchen opened a new issue #6689:
URL: https://github.com/apache/incubator-tvm/issues/6689
https://ci.tlcpack.ai/job/tvm/job/main/19/execution/node/380/log/
Could due to too close ties, perhaps we should construct nms test-cases
differently that have no clear ties
tqchen commented on issue #6689:
URL: https://github.com/apache/incubator-tvm/issues/6689#issuecomment-709316506
cc @masahi @Laurawly
This is an automated message from the Apache Git Service.
To respond to the message,
tqchen commented on issue #6417:
URL: https://github.com/apache/incubator-tvm/issues/6417#issuecomment-709314955
ping @leandron :)
This is an automated message from the Apache Git Service.
To respond to the message, please
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from c7ff885 Add µTVM Zephyr support + QEMU regression test (#6603)
add b121278 int32 pooling with int64
tqchen merged pull request #6687:
URL: https://github.com/apache/incubator-tvm/pull/6687
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
ANSHUMAN87 commented on pull request #6685:
URL: https://github.com/apache/incubator-tvm/pull/6685#issuecomment-709001815
Looks like Tensorflow version in CI is older, may be we need to bump it!!!
This is an automated
liangfu edited a comment on pull request #9:
URL: https://github.com/apache/incubator-tvm-vta/pull/9#issuecomment-706899033
ci tests failed on tsim seems to be unrelated, @zhanghaohit do you mind
retrigger ci to see if it succeeds. (It was [successful
liangfu commented on pull request #6603:
URL: https://github.com/apache/incubator-tvm/pull/6603#issuecomment-708971948
Thanks @areusch @tqchen . This is now merged.
This is an automated message from the Apache Git Service.
liangfu merged pull request #6603:
URL: https://github.com/apache/incubator-tvm/pull/6603
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
This is an automated email from the ASF dual-hosted git repository.
liangfu pushed a change to branch main
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 9564925 [Relay][Frontend][Onnx] Allow A to B broadcasting of
batch_matmul and reverse strided slice (#6681)
liangfu commented on a change in pull request #6603:
URL: https://github.com/apache/incubator-tvm/pull/6603#discussion_r505293470
##
File path: tests/python/unittest/test_micro_artifact.py
##
@@ -0,0 +1,137 @@
+# Licensed to the Apache Software Foundation (ASF) under one
+# or
i24361 opened a new pull request #6688:
URL: https://github.com/apache/incubator-tvm/pull/6688
[TUTORIAL][FIX] Fix VTA autotuning from tutorial fails with one PYNQ, but
succeeds with two PYNQs
https://discuss.tvm.apache.org/t/vta-workaround-for-autotuning-with-one-pynq-z1-board/8091
comaniac commented on a change in pull request #6686:
URL: https://github.com/apache/incubator-tvm/pull/6686#discussion_r505272389
##
File path: src/te/schedule/schedule_dataflow_rewrite.cc
##
@@ -138,6 +138,15 @@ Tensor Schedule::cache_read(const Tensor& tensor, const
jcf94 commented on a change in pull request #6686:
URL: https://github.com/apache/incubator-tvm/pull/6686#discussion_r505237035
##
File path: src/auto_scheduler/compute_dag.cc
##
@@ -970,8 +1005,21 @@ void ComputeDAG::RewriteLayout(const Array&
transform_steps) {
} //
55 matches
Mail list logo