csullivan opened a new pull request #6276:
URL: https://github.com/apache/incubator-tvm/pull/6276
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL a
652994331 commented on issue #4464:
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-673920246
@tobegit3hub and here is the entire cmake log:
udo cmake ..
-- The C compiler identification is GNU 6.4.0
-- The CXX compiler identification is GNU 6.4.0
-- Check
652994331 commented on issue #4464:
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-673919658
@tobegit3hub i tried before, but unfortunately, i had this error:
Traceback (most recent call last):
File "", line 1, in
ModuleNotFoundError: No module named 'tens
kevinthesun commented on issue #6263:
URL: https://github.com/apache/incubator-tvm/issues/6263#issuecomment-673909961
What is the original ```end```? Usually -1 means the end of that dimension.
This is an automated message fr
tobegit3hub edited a comment on issue #4464:
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-673908609
@652994331 You should not use `tftvm` which is deprecated and please rebuild
TVM with `USE_TF_TVMSOOP=ON`. Here is the complete tutorial
https://discuss.tvm.ai/t/add
tobegit3hub commented on issue #4464:
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-673908609
@652994331 You should not `tftvm` which is deprecated and please rebuild TVM
with `USE_TF_TVMSOOP=ON`.
Thi
652994331 commented on issue #4464:
URL: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-673897424
@tobegit3hub Hi guys, i built tvm before and i built tvmsoop separately(not
from USE_TF_TVMSOOP=ON) follow
this:https://github.com/tobegit3hub/tftvm/tree/master/examples .
jcf94 opened a new pull request #6275:
URL: https://github.com/apache/incubator-tvm/pull/6275
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 closed issue #4962:
URL: https://github.com/apache/incubator-tvm/issues/4962
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
masahi merged pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267
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 g
masahi commented on pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#issuecomment-673889169
Thanks @wjliu1998 @leandron
This is an automated message from the Apache Git Service.
To respond to the me
This is an automated email from the ASF dual-hosted git repository.
masahi 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 ad0dbe0 add dilation in x86 NCHWc depthw
hypercubestart commented on a change in pull request #5812:
URL: https://github.com/apache/incubator-tvm/pull/5812#discussion_r470398943
##
File path: tests/python/unittest/test_custom_datatypes.py
##
@@ -0,0 +1,407 @@
+# Licensed to the Apache Software Foundation (ASF) under o
FrozenGene commented on pull request #5913:
URL: https://github.com/apache/incubator-tvm/pull/5913#issuecomment-673871333
@tqchen @merrymercy gental ping. Code has been updated.
This is an automated message from the Apache Gi
shalushajan95 commented on issue #6265:
URL: https://github.com/apache/incubator-tvm/issues/6265#issuecomment-673869168
Hi @bwang1991 is there any way to solve this issue.
This is an automated message from the Apache Git
domin1985 closed pull request #6271:
URL: https://github.com/apache/incubator-tvm/pull/6271
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 t
wjliu1998 commented on pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#issuecomment-673830644
> @wjliu1998 Thanks, please update the PyTorch frontend test below that has
been disabled due to the lack of dilation support in x86:
>
>
https://github.com/apach
bwang1991 commented on issue #6265:
URL: https://github.com/apache/incubator-tvm/issues/6265#issuecomment-673778817
I got a similar error. It looks like hat keys that contain "shape" can cause
KeyErrors.
This is an automated
jroesch opened a new pull request #6274:
URL: https://github.com/apache/incubator-tvm/pull/6274
This is currently a draft PR on the 3rd stage of my parser/diagnostics
refactoring. I will update this with more details as I go.
--
masahi commented on issue #6268:
URL: https://github.com/apache/incubator-tvm/issues/6268#issuecomment-673729436
I can see why this error is happening. We need to pass the Prelude module to
`infer_shape`, `mod` argument here
https://github.com/apache/incubator-tvm/blob/master/python/tvm/re
masahi commented on pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#issuecomment-673727099
@wjliu1998 Thanks, please update the PyTorch frontend test below that has
been disabled due to the lack of dilation support in x86:
https://github.com/apache/incubat
electriclilies opened a new pull request #6273:
URL: https://github.com/apache/incubator-tvm/pull/6273
Implements the dynamic version of the upsampling op
This is an automated message from the Apache Git Service.
To respo
mbrookhart opened a new pull request #6272:
URL: https://github.com/apache/incubator-tvm/pull/6272
Fixes #6263
ToScalar was casting a 64 bit Int to a 64 bit float, which reduced precision
too much. I switched things to use int64_t/long double where needed to keep
precision.
mbrookhart removed a comment on issue #6263:
URL: https://github.com/apache/incubator-tvm/issues/6263#issuecomment-673671138
The onnx importer was casting the value to int32_t, leading to the -1
through overflow. If I change the importer to use int64_t, it rounds to zero
when we convert th
comaniac commented on a change in pull request #6218:
URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r470212475
##
File path: src/target/target.cc
##
@@ -162,14 +314,164 @@ Target Target::Create(const String& target_str) {
return CreateTarget(splits[0], {s
junrushao1994 commented on a change in pull request #6218:
URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r470201050
##
File path: src/target/target.cc
##
@@ -162,14 +314,164 @@ Target Target::Create(const String& target_str) {
return CreateTarget(splits[0
junrushao1994 commented on a change in pull request #6218:
URL: https://github.com/apache/incubator-tvm/pull/6218#discussion_r470201050
##
File path: src/target/target.cc
##
@@ -162,14 +314,164 @@ Target Target::Create(const String& target_str) {
return CreateTarget(splits[0
mbrookhart commented on issue #6263:
URL: https://github.com/apache/incubator-tvm/issues/6263#issuecomment-673671138
The onnx importer was casting the value to int32_t, leading to the -1
through overflow. If I change the importer to use int64_t, it rounds to zero
when we convert the consta
yzhliu commented on a change in pull request #6078:
URL: https://github.com/apache/incubator-tvm/pull/6078#discussion_r470193800
##
File path: include/tvm/node/container.h
##
@@ -1439,6 +1427,22 @@ class Map : public ObjectRef {
MapNode* GetMapNode() const { return static_ca
comaniac commented on a change in pull request #6270:
URL: https://github.com/apache/incubator-tvm/pull/6270#discussion_r470071293
##
File path: python/tvm/auto_scheduler/auto_schedule.py
##
@@ -161,7 +161,7 @@ def __init__(self, task, schedule_cost_model=RandomModel(),
params
weberlo edited a comment on pull request #5940:
URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-673580414
> @weberlo I believe we would like a general approach to achieve the
partitioning in the future, but I am fine with the PR in the current stage. I
will approve it a
weberlo commented on pull request #5940:
URL: https://github.com/apache/incubator-tvm/pull/5940#issuecomment-673580414
> @weberlo I believe we would like a general approach to achieve the
partitioning in the future, but I am fine with the PR in the current stage. I
will approve it after it
zhiics merged pull request #6254:
URL: https://github.com/apache/incubator-tvm/pull/6254
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 g
zhiics commented on pull request #6254:
URL: https://github.com/apache/incubator-tvm/pull/6254#issuecomment-673574279
Thanks @lhutton1 @comaniac
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.
zhic pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 16b2a4b [Relay][Dyn] Dynamic full operator (#6260)
add 15eef5c [BYOC][ACL] Add support for dense (fully c
zhiics merged pull request #6260:
URL: https://github.com/apache/incubator-tvm/pull/6260
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 g
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 c0d11fd fix cuda half math function is undefined: hpow, htanh (#6253)
add 16b2a4b [Relay][Dyn] Dynamic fu
zhiics commented on pull request #6260:
URL: https://github.com/apache/incubator-tvm/pull/6260#issuecomment-673567688
Thanks @electriclilies @mbrookhart
This is an automated message from the Apache Git Service.
To respond to
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 889d3b6 Trivial fix, up the rodata section for the discovery board to
512 bytes. (#6259)
add c0d11fd f
tqchen merged pull request #6253:
URL: https://github.com/apache/incubator-tvm/pull/6253
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 g
tqchen merged pull request #6264:
URL: https://github.com/apache/incubator-tvm/pull/6264
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 g
tqchen merged pull request #6259:
URL: https://github.com/apache/incubator-tvm/pull/6259
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 g
tqchen commented on pull request #6259:
URL: https://github.com/apache/incubator-tvm/pull/6259#issuecomment-673549135
Thanks @tom-gall !
This is an automated message from the Apache Git Service.
To respond to the message, ple
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 2247a2e [LINT] Fix clang-format (#6264)
add 889d3b6 Trivial fix, up the rodata section for the discover
tqchen closed issue #6246:
URL: https://github.com/apache/incubator-tvm/issues/6246
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
This is an automated email from the ASF dual-hosted git repository.
tqchen pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from b6b5ace Improve NHWC depthwise convolution for AArch64 (#6095)
add 2247a2e [LINT] Fix clang-format (#62
This is an automated email from the ASF dual-hosted git repository.
zhaowu pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from abfa79d update tutorial to new TARGET as micro_dev is no more (#6262)
add b6b5ace Improve NHWC depthwis
FrozenGene commented on pull request #6095:
URL: https://github.com/apache/incubator-tvm/pull/6095#issuecomment-673519634
Thanks @giuseros Merged now
This is an automated message from the Apache Git Service.
To respond to the
FrozenGene merged pull request #6095:
URL: https://github.com/apache/incubator-tvm/pull/6095
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
giuseros commented on pull request #6095:
URL: https://github.com/apache/incubator-tvm/pull/6095#issuecomment-673507098
Hi @FrozenGene , @anijain2305 ,
This PR finally passed the CI. Would it be possible to merge it?
Thanks!
---
leandron commented on a change in pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#discussion_r469978920
##
File path: tests/python/topi/python/test_topi_depthwise_conv2d.py
##
@@ -268,7 +268,7 @@ def depthwise_conv2d_with_workload_NCHWc(batch, in_chan
d-smirnov commented on a change in pull request #6018:
URL: https://github.com/apache/incubator-tvm/pull/6018#discussion_r469979193
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1089,7 +1093,7 @@ def convert_square(self, op):
return out
-def _convert
domin1985 opened a new pull request #6271:
URL: https://github.com/apache/incubator-tvm/pull/6271
Hi,
A tvm error occurred when I imported a pre-trained keras model:
T
jcf94 commented on pull request #6269:
URL: https://github.com/apache/incubator-tvm/pull/6269#issuecomment-673434269
> Please remove the tutorial. It is better to make the tutorials as a single
PR, so people can review it easily and give more suggestions on the API design.
It is not good t
merrymercy edited a comment on pull request #6269:
URL: https://github.com/apache/incubator-tvm/pull/6269#issuecomment-673430973
Please remove the tutorial. It is better to make the tutorials as a single
PR, so people can review it easily and give more suggestions on the API design.
It is
merrymercy edited a comment on pull request #6269:
URL: https://github.com/apache/incubator-tvm/pull/6269#issuecomment-673430973
Please remove the tutorial. It is better to make the tutorials as a single
PR, so people can review it easily and give more suggestions on the API design.
merrymercy commented on pull request #6269:
URL: https://github.com/apache/incubator-tvm/pull/6269#issuecomment-673430973
Please remove the tutorial. It is better to make the tutorials as a single
PR, so people can review it easilly and give more suggestions on the API design.
---
merrymercy opened a new pull request #6270:
URL: https://github.com/apache/incubator-tvm/pull/6270
For the full upstream plan, see [Ansor
RFC](https://discuss.tvm.ai/t/rfc-ansor-an-auto-scheduler-for-tvm-autotvm-v2-0/7005/32).
This PR adds a xgboost-based cost model.
It is similar
merrymercy commented on pull request #6270:
URL: https://github.com/apache/incubator-tvm/pull/6270#issuecomment-673430091
cc @jcf94 @comaniac @junrushao1994 @tqchen
This is an automated message from the Apache Git Service.
T
d-smirnov commented on a change in pull request #6168:
URL: https://github.com/apache/incubator-tvm/pull/6168#discussion_r469886837
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1321,14 +1321,15 @@ def convert_gather(self, op):
input_tensors = self.get_input
lhutton1 commented on a change in pull request #6254:
URL: https://github.com/apache/incubator-tvm/pull/6254#discussion_r469832156
##
File path: python/tvm/relay/op/contrib/arm_compute_lib.py
##
@@ -114,8 +141,26 @@ def check_qnn_conv(extract):
call = call.args[0]
mbaret commented on pull request #6228:
URL: https://github.com/apache/incubator-tvm/pull/6228#issuecomment-673392927
I'm still not really sure what's meant by the 'wrap' and can't find anything
in the tensorflow/tflite docs named that. It appears to just control whether
the input is a con
d-smirnov commented on a change in pull request #6228:
URL: https://github.com/apache/incubator-tvm/pull/6228#discussion_r469846267
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1695,10 +1695,9 @@ def convert_fully_connected(self, op):
raise ImportError(
mbaret commented on a change in pull request #6228:
URL: https://github.com/apache/incubator-tvm/pull/6228#discussion_r469842573
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1695,10 +1695,9 @@ def convert_fully_connected(self, op):
raise ImportError("Th
lhutton1 commented on a change in pull request #6254:
URL: https://github.com/apache/incubator-tvm/pull/6254#discussion_r469832156
##
File path: python/tvm/relay/op/contrib/arm_compute_lib.py
##
@@ -114,8 +141,26 @@ def check_qnn_conv(extract):
call = call.args[0]
lhutton1 commented on a change in pull request #6248:
URL: https://github.com/apache/incubator-tvm/pull/6248#discussion_r469831401
##
File path: tests/python/contrib/test_arm_compute_lib/test_pooling.py
##
@@ -74,53 +142,133 @@ def test_pooling():
device = Device()
np
wjliu1998 commented on a change in pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#discussion_r469813115
##
File path: tests/python/topi/python/test_topi_depthwise_conv2d.py
##
@@ -268,7 +268,7 @@ def depthwise_conv2d_with_workload_NCHWc(batch, in_cha
leandron commented on a change in pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267#discussion_r469791300
##
File path: python/tvm/topi/x86/depthwise_conv2d.py
##
@@ -122,13 +122,24 @@ def depthwise_conv2d_NCHWc(cfg, data, kernel, strides,
padding, dil
jcf94 opened a new pull request #6269:
URL: https://github.com/apache/incubator-tvm/pull/6269
For full upstream plan, see [Ansor
RFC](https://discuss.tvm.ai/t/rfc-ansor-an-auto-scheduler-for-tvm-autotvm-v2-0/7005/32).
In this PR, we bring the basic Sketch search policy which is propo
nolanliou opened a new issue #6268:
URL: https://github.com/apache/incubator-tvm/issues/6268
When I convert a PyTorch Bert model to TVM, there is a problem blow
```
File "tvm/python/tvm/relay/frontend/pytorch.py", line 2673, in from_pytorch
default_dtype=default_dtype)
Fi
wjliu1998 opened a new pull request #6267:
URL: https://github.com/apache/incubator-tvm/pull/6267
as mentioned in #4962 (https://github.com/apache/incubator-tvm/issues/4962),
the NCHWc depthwise convolution does not support dilation > 1.
The problem has been fixed
-
vadimsightx commented on issue #6258:
URL: https://github.com/apache/incubator-tvm/issues/6258#issuecomment-673302594
rebuild and works now thanks
This is an automated message from the Apache Git Service.
To respond to the me
vadimsightx removed a comment on issue #6258:
URL: https://github.com/apache/incubator-tvm/issues/6258#issuecomment-673290080
> Hi @vadimsightx. Can you provide a bit more context on how you built TVM,
in terms of CMake flags, etc?
# Licensed to the Apache Software Foundation (ASF) under
73 matches
Mail list logo
