icemelon9 commented on issue #4764: [CI] ci-gpu update blockers
URL: https://github.com/apache/incubator-tvm/issues/4764#issuecomment-580592009
One work around is that we can use the latest build of mxnet-mkl, which has
fixed the problem.
```
pip install
https://apache-mxnet.s3-us-
FrozenGene commented on a change in pull request #4790: Fast exponent
URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r37330
##
File path: topi/include/topi/elemwise.h
##
@@ -360,5 +359,71 @@ inline Tensor full_like(const Tensor& x,
}, name, tag);
tqchen commented on issue #4764: [CI] ci-gpu update blockers
URL: https://github.com/apache/incubator-tvm/issues/4764#issuecomment-580558384
given that the mkl part poses accuracy problem, i feel it might be a bad
idea to rely on it for testing QNN(see also comment about intel dependency).
alexwong commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580519028
> actually I cannot run torchvision tests in this PR on my 8GB laptop. Maybe
RAM is the problem?
Yeah I think it's something al
masahi commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580517710
actually I cannot run torchvision tests in this PR on my 8GB laptop. Maybe
RAM is the problem?
alexwong commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580517249
My local test (using CI container) passes but it fails here due to an out of
memory issue so I think it is an issue with not enough me
zxy844288792 commented on a change in pull request #4787: [Relay] Conv2D
padding representation
URL: https://github.com/apache/incubator-tvm/pull/4787#discussion_r373255718
##
File path: topi/python/topi/nn/conv2d.py
##
@@ -62,6 +61,8 @@ def conv2d(input, filter, strides,
gussmith23 commented on issue #4568: [Feature] Support for NonZero ONNX operator
URL: https://github.com/apache/incubator-tvm/issues/4568#issuecomment-580510543
I've been trying to get a GNMT model importing into Relay. The ONNX route
seems the most pain-free; however, this is a blocking is
huajsj commented on issue #4791: [TOPI] upsample operator 'NCHWinic' format
support.
URL: https://github.com/apache/incubator-tvm/pull/4791#issuecomment-580493189
Hi @Laurawly @Huyuwei , could you help for the review thanks.
alexwong commented on a change in pull request #4497: [WIP] [Relay] Add a
PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r373217425
##
File path: python/tvm/relay/frontend/pytorch.py
##
@@ -0,0 +1,1084 @@
+# Licensed to the Apache
comaniac commented on a change in pull request #4787: [Relay] Conv2D padding
representation
URL: https://github.com/apache/incubator-tvm/pull/4787#discussion_r373193490
##
File path: topi/python/topi/nn/conv2d.py
##
@@ -62,6 +61,8 @@ def conv2d(input, filter, strides, padd
icemelon9 edited a comment on issue #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#issuecomment-579944529
I've added the strategy for all ops. We can start to review this PR since
it's huge. Could you help review it?
@tqchen @kevinthesun @comaniac @
icemelon9 commented on a change in pull request #4787: [Relay] Conv2D padding
representation
URL: https://github.com/apache/incubator-tvm/pull/4787#discussion_r373190892
##
File path: topi/python/topi/nn/conv2d.py
##
@@ -62,6 +61,8 @@ def conv2d(input, filter, strides, pad
jwfromm commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580456133
@alexwong the new refactored tests look so much better!
This is an aut
jwfromm commented on a change in pull request #4497: [WIP] [Relay] Add a
PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r373186300
##
File path: tests/python/frontend/pytorch/test_forward_refactor.py
##
@@ -0,0 +1,813 @@
+# Licens
jwfromm commented on a change in pull request #4497: [WIP] [Relay] Add a
PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#discussion_r373186048
##
File path: tests/python/frontend/pytorch/test_forward_refactor.py
##
@@ -0,0 +1,813 @@
+# Licens
alexgl-github commented on a change in pull request #4790: Fast exponent
URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r373157363
##
File path: topi/include/topi/elemwise.h
##
@@ -360,5 +359,71 @@ inline Tensor full_like(const Tensor& x,
}, name, tag)
alexgl-github commented on a change in pull request #4790: Fast exponent
URL: https://github.com/apache/incubator-tvm/pull/4790#discussion_r373157363
##
File path: topi/include/topi/elemwise.h
##
@@ -360,5 +359,71 @@ inline Tensor full_like(const Tensor& x,
}, name, tag)
alexgl-github commented on a change in pull request #4775: conv3d_ndhwc schedule
URL: https://github.com/apache/incubator-tvm/pull/4775#discussion_r373155323
##
File path: topi/python/topi/x86/conv3d.py
##
@@ -0,0 +1,112 @@
+# Licensed to the Apache Software Foundation (ASF
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373142619
##
File path: python/tvm/relay/backend/compile_engine.py
##
@@ -63,6 +83,316 @@ def _get_cache_key(source_func, target
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373142390
##
File path: python/tvm/relay/quantize/_annotate.py
##
@@ -53,11 +53,11 @@ def simulated_quantize_compute(attrs, inpu
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373142456
##
File path: python/tvm/autotvm/task/task.py
##
@@ -116,43 +149,134 @@ def __repr__(self):
self.name, se
comaniac commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373142087
##
File path: python/tvm/autotvm/task/dispatcher.py
##
@@ -481,8 +412,12 @@ def _query_inside(self, target, workload):
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373141667
##
File path: python/tvm/relay/backend/compile_engine.py
##
@@ -63,6 +83,316 @@ def _get_cache_key(source_func, target
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373139677
##
File path: python/tvm/autotvm/task/dispatcher.py
##
@@ -481,8 +412,12 @@ def _query_inside(self, target, workload):
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373139677
##
File path: python/tvm/autotvm/task/dispatcher.py
##
@@ -481,8 +412,12 @@ def _query_inside(self, target, workload):
This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch master
in repository https://gitbox.apache.org/repos/asf/incubator-tvm.git.
from 24126b4 Fix parsing of different exception string formats (#4785)
add 10f85d0 Dedup BindParamByName fun
masahi merged pull request #4793: [Relay] Remove duplicated BindParamByName
function in VM compiler
URL: https://github.com/apache/incubator-tvm/pull/4793
This is an automated message from the Apache Git Service.
To respond
icemelon9 commented on a change in pull request #4644: [WIP] Relay op strategy
URL: https://github.com/apache/incubator-tvm/pull/4644#discussion_r373136444
##
File path: python/tvm/relay/backend/compile_engine.py
##
@@ -63,6 +83,316 @@ def _get_cache_key(source_func, target
alexwong commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580391605
> @alexwong the CI is not updated even if you update the docker script in
this PR (see https://docs.tvm.ai/contribute/pull_request.htm
abergeron commented on issue #4758: [relay] PrimitiveInliner doesn't correctly
handle match expressions that have more than one use
URL: https://github.com/apache/incubator-tvm/issues/4758#issuecomment-580367317
Fixed by #4783
--
abergeron closed issue #4758: [relay] PrimitiveInliner doesn't correctly handle
match expressions that have more than one use
URL: https://github.com/apache/incubator-tvm/issues/4758
This is an automated message from the Apa
comaniac commented on a change in pull request #4787: [Relay] Conv2D padding
representation
URL: https://github.com/apache/incubator-tvm/pull/4787#discussion_r373085568
##
File path: topi/python/topi/nn/conv2d.py
##
@@ -62,6 +61,8 @@ def conv2d(input, filter, strides, padd
FrozenGene merged pull request #4785: [FFI][Windows] Parse additional exception
strings
URL: https://github.com/apache/incubator-tvm/pull/4785
This is an automated message from the Apache Git Service.
To respond to the messa
FrozenGene commented on issue #4785: [FFI][Windows] Parse additional exception
strings
URL: https://github.com/apache/incubator-tvm/pull/4785#issuecomment-580344098
Thanks @jmorrill @soiferj This is merged now.
This is an aut
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 6914963 [Relay][Frontend][TFlite] Add add parser support for
relational ops (#4695)
add 24126b4 Fix pa
soiferj commented on issue #4785: [FFI][Windows] Parse additional exception
strings
URL: https://github.com/apache/incubator-tvm/pull/4785#issuecomment-580339270
@FrozenGene that’s how I approved the changes yesterday! Above my comment I
see the message “soiferj approved these changes”. Fe
expectopatronm commented on issue #1027: TVMError:
src/runtime/cuda/cuda_module.cc:93: CUDAError:
cuModuleLoadData(&(module_[device_id]), data_.c_str()) failed with error:
CUDA_ERROR_INVALID_PTX
URL: https://github.com/apache/incubator-tvm/issues/1027#issuecomment-580311728
I get the exac
FrozenGene commented on a change in pull request #4543: [FRONTEND][TFLITE] Add
support for TFLite_Detection_PostProcess
URL: https://github.com/apache/incubator-tvm/pull/4543#discussion_r372971382
##
File path: python/tvm/relay/frontend/tflite.py
##
@@ -1662,6 +1667,112 @@
FrozenGene commented on issue #4695: [Relay][Frontend][TFlite] Add parser
support for relational ops
URL: https://github.com/apache/incubator-tvm/pull/4695#issuecomment-580271032
Thanks @inadob @wyc-ruiker This is merged now.
FrozenGene merged pull request #4695: [Relay][Frontend][TFlite] Add parser
support for relational ops
URL: https://github.com/apache/incubator-tvm/pull/4695
This is an automated message from the Apache Git Service.
To respon
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 6914963 [Relay][Frontend][TFlite] Add ad
masahi commented on issue #4756: [Docker] Update torch version to 1.4
URL: https://github.com/apache/incubator-tvm/pull/4756#issuecomment-580259814
ok CI is fixed.
@tqchen since the update of MXNet seems to be having issues, and we want to
test the [PyTorch frontend](https://github.
masahi commented on issue #4497: [WIP] [Relay] Add a PyTorch to Relay Parser
URL: https://github.com/apache/incubator-tvm/pull/4497#issuecomment-580244271
@alexwong the CI is not updated even if you update the docker script in this
PR (see https://docs.tvm.ai/contribute/pull_request.html#ci
masahi opened a new pull request #4793: Dedup BindParamByName function in VM
compiler
URL: https://github.com/apache/incubator-tvm/pull/4793
Thanks for contributing to TVM! Please refer to guideline
https://docs.tvm.ai/contribute/ for useful information and tips. After the pull
request
masahi commented on issue #4792: [Tutorial, VTA] Fix param name for autotvm
function
URL: https://github.com/apache/incubator-tvm/pull/4792#issuecomment-580222718
I realized I'd better fix this in my existing PR #4756 that is blocked by
this bug
--
masahi closed pull request #4792: [Tutorial, VTA] Fix param name for autotvm
function
URL: https://github.com/apache/incubator-tvm/pull/4792
This is an automated message from the Apache Git Service.
To respond to the message
masahi opened a new pull request #4792: [Tutorial, VTA] Fix param name for
autotvm function
URL: https://github.com/apache/incubator-tvm/pull/4792
Thanks for contributing to TVM! Please refer to guideline
https://docs.tvm.ai/contribute/ for useful information and tips. After the pull
re
inadob commented on a change in pull request #4695: [Relay][Frontend][TFlite]
Add parser support for relational ops
URL: https://github.com/apache/incubator-tvm/pull/4695#discussion_r372861913
##
File path: tests/python/frontend/tflite/test_forward.py
##
@@ -843,6 +843,13
49 matches
Mail list logo